Showing 1–50 of 53 results for author: Vyas, S

Vision-Language Models for Analog Gauge Reading: An Empirical Study of Specialization, Transfer and Reliability

Authors: Abdul Mueez, Aaditya Baranwal, Junior Chaj-Mejia, Guneet Bhatia, Jason T. Voelker, Shruti Vyas

Abstract: Analog gauges remain common in industrial environments where manual inspection is costly or hazardous. The engineering application addressed here is direct numerical reading of single-target analog-gauge images, while the artificial-intelligence contribution is a systematic evaluation of specialization, transfer, robustness and reliability for a general-purpose vision-language model (VLM) without… ▽ More Analog gauges remain common in industrial environments where manual inspection is costly or hazardous. The engineering application addressed here is direct numerical reading of single-target analog-gauge images, while the artificial-intelligence contribution is a systematic evaluation of specialization, transfer, robustness and reliability for a general-purpose vision-language model (VLM) without an explicit pointer-segmentation and geometric-reading pipeline. The Qwen2.5-VL-7B-Instruct model is evaluated using zero-shot prompting, in-context learning (ICL) and parameter-efficient fine-tuning with Quantized Low-Rank Adaptation (QLoRA) on a public synthetic dataset, a video-derived Pressure Gauge dataset and a proprietary industrial dataset. All fine-tuning experiments use a fixed 20-epoch protocol with the final epoch used for analysis; separate models with and without supplied gauge ranges remove prompt-setting confounds. The primary metric is range-normalized mean percentage error (MPE). The best fine-tuned MPE values are 2.39% on the synthetic dataset, with a 95% bootstrap confidence interval (CI) of 1.43-3.90%; 2.61% on the Pressure Gauge dataset, with a CI of 1.66-3.80%; and 4.43% on the proprietary industrial dataset, with a CI of 2.31-7.14%. Leave-one-dataset-out experiments reveal substantial transfer degradation on held-out synthetic and proprietary data, while robustness tests identify Gaussian blur as the strongest tested corruption. Reliability analysis shows that high-confidence errors remain possible, motivating abstention and independent validation in safety-critical use. These results support QLoRA-specialized VLMs for direct single-gauge reading but not yet a deployment-ready plant-monitoring pipeline. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Comments: Submitted to Engineering Applications of Artificial Intelligence

A Generative Approach for Improving Multi-Label Defect Classification in Photovoltaic Modules

Authors: Abdul Mueez, Yogesh S. Rawat, Shruti Vyas

Abstract: This paper addresses the challenge of multi-label defect classification in electroluminescence (EL) images of photovoltaic (PV) cells. Training models on images where multiple defects co-occur creates learning ambiguity, making it difficult to disentangle visual features for specific defect types, a problem compounded by the scarcity of examples for individual classes. To tackle this, we introduce… ▽ More This paper addresses the challenge of multi-label defect classification in electroluminescence (EL) images of photovoltaic (PV) cells. Training models on images where multiple defects co-occur creates learning ambiguity, making it difficult to disentangle visual features for specific defect types, a problem compounded by the scarcity of examples for individual classes. To tackle this, we introduce Generative Defect Isolation (GDI), utilizing the LaMa inpainting model with Fast Fourier Convolutions to remove selected defects and generate realistic, single-defect training samples. Extensive experiments on Vision Transformer (ViT-S, ViT-L) and EfficientNetV2-L architectures demonstrate that GDI significantly outperforms baselines. The performance gains are most pronounced in low-data scenarios; class-wise analysis shows substantial improvements, boosting the F1-Score for rare defect classes by up to 63.6%. Furthermore, GDI effectively resolves learning ambiguity from co-occurring defects, yielding a 26% reduction in such co-occurring classification errors. Our work establishes GDI as an effective method for maximizing the value of existing segmentation datasets and sets a new performance benchmark for multi-label classification in this domain. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Journal ref: Solar Energy 317 (2026) 114943

Robust Onion: Peeling Open Vocab Object Detectors Under Noise

Authors: Priyank Pathak, Mukilan Karuppasamy, Aaditya Baranwal, Shruti Vyas, Yogesh S Rawat

Abstract: The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity. We present our comprehensive analysis Robust Onion, an empirical study that uses controlled synthetic visual degradations to peel OV-ODs layer-by-layer, revealing how, why, and where robustness degrades, systematically analyzing feature collapse. Our findings… ▽ More The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity. We present our comprehensive analysis Robust Onion, an empirical study that uses controlled synthetic visual degradations to peel OV-ODs layer-by-layer, revealing how, why, and where robustness degrades, systematically analyzing feature collapse. Our findings reveal that models with similar vision backbones exhibit comparable robustness, driven by similar feature collapse at similar layers, while factors such as pretraining strategy, architectural nuances, and caption supervision contribute little. Robustness is primarily governed by the image domain rather than annotations, explaining the similar robustness impact on COCO and LVIS, and why datasets like ODinW-13 can give an impression of inflated robustness due to large, isolated objects. Finally, we validate our insights by improving robustness on real-world BDD100K, WiderFace, and VisDRONE via our lightweight plug-and-play NN & TK0 approach, using 96x fewer trainable parameters than end-to-end training. We also explain the prior works' robustness observations. △ Less

Submitted 26 June, 2026; v1 submitted 25 June, 2026; originally announced June 2026.

Comments: Accepted at The 19th European Conference on Computer Vision (ECCV)

PHOEBI: An Open-World Benchmark for Bacterial Identification in Phase-Contrast Microscopy

Authors: Aaditya Baranwal, Md Jahid Hasan, Shruti Vyas

Abstract: Optical microscopy enables rapid, label-free imaging of live bacteria and is the standard instrument for species identification across clinical, environmental, and industrial microbiology. Yet field samples are routinely polymicrobial and may contain organisms that were never seen during system training, and no computer-vision benchmark tests multi-label species identification from phase-contrast… ▽ More Optical microscopy enables rapid, label-free imaging of live bacteria and is the standard instrument for species identification across clinical, environmental, and industrial microbiology. Yet field samples are routinely polymicrobial and may contain organisms that were never seen during system training, and no computer-vision benchmark tests multi-label species identification from phase-contrast microscopy (PCM) of such mixtures. We introduce Phase-contrast Optical bEnchmark for Bacterial Identification ($\textbf{PHOEBI}$), a wet-lab-prepared dataset of $120{,}000$ PCM images covering $40$ combinations of six rod-shaped species, paired with a leave-combinations-out (LCO) evaluation protocol that holds out entire species combinations to mirror the practical scenario of a model trained on catalogued mixtures that must generalise to unseen ones. On LCO, every gradient-trained per-image aggregator we test drops $0.39$ to $0.57$ F1 from the in-distribution to the held-out split, a systematic open-world recognition failure in the aggregator, not the visual representation. A linear probe of thirteen different encoders over the same features spreads only about six percentage points of F1 across general-purpose and biomedical pretraining objectives, confirming the representation is sound. We propose three lightweight $\textit{anchor-based}$ decoders that capture per-species presence geometrically over a shared frozen tile-feature pool, scoring $\textit{higher}$ on held-out combinations than on in-distribution validation. △ Less

Submitted 22 June, 2026; originally announced June 2026.

MolSight: Molecular Property Prediction with Images

Authors: Aaditya Baranwal, Akshaj Gupta, Yogesh S Rawat, Shruti Vyas

Abstract: Every molecule ever synthesised can be drawn as a 2D skeletal diagram, yet in modern property prediction this universally available representation has received less focus in favour of molecular graphs, 3D conformers, or billion-parameter language models, each imposing its own computational and data-engineering overhead. We present $\textbf{MolSight}$, the first systematic large-scale study of visi… ▽ More Every molecule ever synthesised can be drawn as a 2D skeletal diagram, yet in modern property prediction this universally available representation has received less focus in favour of molecular graphs, 3D conformers, or billion-parameter language models, each imposing its own computational and data-engineering overhead. We present $\textbf{MolSight}$, the first systematic large-scale study of vision-based Molecular Property Prediction (MPP). Using 10 vision architectures, 7 pre-training strategies, and $2\,M$ molecule images, we evaluate performance across 10 downstream tasks spanning physical-property regression, drug-discovery classification, and quantum-chemistry prediction. To account for the wide variation in structural complexity across pre-training molecules, we further propose a $\textbf{chemistry-informed curriculum}$: five structural complexity descriptors partition the corpus into five tiers of increasing chemical difficulty, consistently outperforming non-curriculum baselines. We show that a single rendered bond-line image, processed by a vision encoder, is sufficient for competitive molecular property prediction, i.e. $\textit{chemical insight from sight alone}$. The best curriculum-trained configuration achieves the top result on $\textbf{5 of 10}$ benchmarks and top two on $\textbf{all 10}$, at $\textbf{$\textit{80$\times$ lower}$}$ FLOPs than the nearest multi-modal competitor. △ Less

Submitted 14 June, 2026; v1 submitted 11 May, 2026; originally announced May 2026.

Right Model, Right Time: Real-Time Cascaded-Fidelity MPC for Bipedal Walking

Authors: Franek Stark, Felix Wiebe, Shubham Vyas, Dennis Mronga, Frank Kirchner

Abstract: This paper presents a multi-phase whole-body model predictive control (MPC) approach for bipedal walking, combining a detailed whole-body model in the near horizon with a simplified single-rigid-body model in the later prediction steps. This reduces computational complexity while retaining prediction capabilities. The resulting nonlinear optimal control problem is solved entirely within the genera… ▽ More This paper presents a multi-phase whole-body model predictive control (MPC) approach for bipedal walking, combining a detailed whole-body model in the near horizon with a simplified single-rigid-body model in the later prediction steps. This reduces computational complexity while retaining prediction capabilities. The resulting nonlinear optimal control problem is solved entirely within the general-purpose, off-the-shelf nonlinear MPC framework acados, using sequential quadratic programming (SQP). Given a contact schedule and a target walking speed, the controller optimizes joint torques without depending on preselected footstep locations. The controller is validated in MuJoCo simulation on the 18-DoF bipedal robot HyPer-2. △ Less

Submitted 3 June, 2026; v1 submitted 6 May, 2026; originally announced May 2026.

Comments: Presented at IEEE ICRA 2026 Workshop "2cnd Workshop on Frontiers of Optimization for Robotics"

Journal ref: Proceedings of the 2nd ICRA Workshop on Frontiers of Optimization for Robotics, 2026

Bridging Foundation Models and ASTM Metallurgical Standards for Automated Grain Size Estimation from Microscopy Images

Authors: Abdul Mueez, Shruti Vyas

Abstract: Extracting standardized metallurgical metrics from microscopy images remains challenging due to complex grain morphology and the data demands of supervised segmentation. To bridge foundational computer vision with practical metallurgical evaluation, we propose an automated pipeline for dense instance segmentation and grain size estimation that adapts Cellpose-SAM to microstructures and integrates… ▽ More Extracting standardized metallurgical metrics from microscopy images remains challenging due to complex grain morphology and the data demands of supervised segmentation. To bridge foundational computer vision with practical metallurgical evaluation, we propose an automated pipeline for dense instance segmentation and grain size estimation that adapts Cellpose-SAM to microstructures and integrates its topology-aware gradient tracking with an ASTM E112 Jeffries planimetric module. We systematically benchmark this pipeline against a classical convolutional network (U-Net), an adaptive-prompting vision foundation model (MatSAM) and a contemporary vision-language model (Qwen2.5-VL-7B). Our evaluations reveal that while the out-of-the-box vision-language model struggles with the localized spatial reasoning required for dense microscopic counting and MatSAM suffers from over-segmentation despite its domain-specific prompt generation, our adapted pipeline successfully maintains topological separation. Furthermore, experiments across progressively reduced training splits demonstrate exceptional few-shot scalability; utilizing only two training samples, the proposed system predicts the ASTM grain size number (G) with a mean absolute percentage error (MAPE) as low as 1.50%, while robustness testing across varying target grain counts empirically validates the ASTM 50-grain sampling minimum. These results highlight the efficacy of application-level foundation model integration for highly accurate, automated materials characterization. Our project repository is available at https://github.com/mueez-overflow/ASTM-Grain-Size-Estimator. △ Less

Submitted 20 April, 2026; originally announced April 2026.

Comments: Accepted at the 11th IEEE Workshop on Computer Vision for Multimodal Microscopy Image Analysis (CVMI), CVPR Workshops 2026

Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization

Authors: Siddhant Bharadwaj, Ashish Vashist, Fahimul Aleem, Shruti Vyas

Abstract: Image geolocalization has traditionally been addressed through retrieval-based place recognition or geometry-based visual localization pipelines. Recent advances in Vision-Language Models (VLMs) have demonstrated strong zero-shot reasoning capabilities across multimodal tasks, yet their performance in geographic inference remains underexplored. In this work, we present a systematic evaluation of m… ▽ More Image geolocalization has traditionally been addressed through retrieval-based place recognition or geometry-based visual localization pipelines. Recent advances in Vision-Language Models (VLMs) have demonstrated strong zero-shot reasoning capabilities across multimodal tasks, yet their performance in geographic inference remains underexplored. In this work, we present a systematic evaluation of multiple state-of-the-art VLMs for country-level image geolocalization using ground-view imagery only. Instead of relying on image matching, GPS metadata, or task-specific training, we evaluate prompt-based country prediction in a zero-shot setting. The selected models are tested on three geographically diverse datasets to assess their robustness and generalization ability. Our results reveal substantial variation across models, highlighting the potential of semantic reasoning for coarse geolocalization and the limitations of current VLMs in capturing fine-grained geographic cues. This study provides the first focused comparison of modern VLMs for country-level geolocalization and establishes a foundation for future research at the intersection of multimodal reasoning and geographic understanding. △ Less

Submitted 17 April, 2026; originally announced April 2026.

Comments: Accepted to the CVPR EarthVision 2026 Workshop

Toward using Speech to Sense Student Emotion in Remote Learning Environments

Authors: Sargam Vyas, Bogdan Vlasenko, André Mayoraz, Egon Werlen, Per Bergamin, Mathew Magimai. -Doss

Abstract: With advancements in multimodal communication technologies, remote learning environments such as, distance universities are increasing. Remote learning typically happens asynchronously. As a consequence, unlike face-to-face in-person classroom teaching, this lacks availability of sufficient emotional cues for making learning a pleasant experience. Motivated by advances made in the paralinguistic s… ▽ More With advancements in multimodal communication technologies, remote learning environments such as, distance universities are increasing. Remote learning typically happens asynchronously. As a consequence, unlike face-to-face in-person classroom teaching, this lacks availability of sufficient emotional cues for making learning a pleasant experience. Motivated by advances made in the paralinguistic speech processing community on emotion prediction, in this paper we explore use of speech for sensing students' emotions by building upon speech-based self-control tasks developed to aid effective remote learning. More precisely, we investigate: (a) whether speech acquired through self-control tasks exhibit perceptible variation along valence, arousal, and dominance dimensions? and (b) whether those dimensional emotion variations can be automatically predicted? We address these two research questions by developing a dataset containing spontaneous monologue speech acquired as open responses to self-control tasks and by carrying out subjective listener evaluations and automatic dimensional emotion prediction studies on that dataset. Our investigations indicate that speech-based self-control tasks can be a means to sense student emotion in remote learning environment. This opens potential venues to seamlessly integrate paralinguistic speech processing technologies in the remote learning loop for enhancing learning experiences through instructional design and feedback generation. △ Less

Submitted 10 April, 2026; originally announced April 2026.

Mixed-Integer vs. Continuous Model Predictive Control for Binary Thrusters: A Comparative Study

Authors: Franek Stark, Jakob Middelberg, Shubham Vyas

Abstract: Binary on/off thrusters are commonly used for spacecraft attitude and position control during proximity operations. However, their discrete nature poses challenges for conventional continuous control methods. The control of these discrete actuators is either explicitly formulated as a mixed-integer optimization problem or handled in a two-layer approach, where a continuous controller's output is c… ▽ More Binary on/off thrusters are commonly used for spacecraft attitude and position control during proximity operations. However, their discrete nature poses challenges for conventional continuous control methods. The control of these discrete actuators is either explicitly formulated as a mixed-integer optimization problem or handled in a two-layer approach, where a continuous controller's output is converted to binary commands using analog-to digital modulation techniques such as Delta-Sigma-modulation. This paper provides the first systematic comparison between these two paradigms for binary thruster control, contrasting continuous Model Predictive Control (MPC) with Delta-Sigma modulation against direct Mixed-Integer MPC (MIMPC) approaches. Furthermore, we propose a new variant of MPC for binary actuated systems, which is informed using the state of the Delta-Sigma Modulator. The two variations for the continuous MPC along with the MIMPC are evaluated through extensive simulations using ESA's REACSA platform. Results demonstrate that while all approaches perform similarly in high-thrust regimes, MIMPC achieves superior fuel efficiency in low-thrust conditions. Continuous MPC with modulation shows instabilities at higher thrust levels, while binary informed MPC, which incorporates modulator dynamics, improves robustness and reduces the efficiency gap to the MIMPC. It can be seen from the simulated and real-system experiments that MIMPC offers complete stability and fuel efficiency benefits, particularly for resource-constrained missions, while continuous control methods remain attractive for computationally limited applications. △ Less

Submitted 14 April, 2026; v1 submitted 20 March, 2026; originally announced March 2026.

Comments: Accepted to CEAS EuroGNC 2026

SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity

Authors: Shae McFadden, Myles Foley, Elizabeth Bates, Ilias Tsingenopoulos, Sanyam Vyas, Vasilios Mavroudis, Chris Hicks, Fabio Pierazzi

Abstract: Deep Reinforcement Learning (DRL) has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, transitioning DRL from laboratory simulations to bespoke cyber environments can introduce numerous issues. This is further exacerbated by the often adversarial, non-stationary, and partially-observable nature of most cyber… ▽ More Deep Reinforcement Learning (DRL) has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, transitioning DRL from laboratory simulations to bespoke cyber environments can introduce numerous issues. This is further exacerbated by the often adversarial, non-stationary, and partially-observable nature of most cybersecurity tasks. In this paper, we identify and systematize 11 methodological pitfalls that frequently occur in DRL for cybersecurity (DRL4Sec) literature across the stages of environment modeling, agent training, performance evaluation, and system deployment. By analyzing 66 significant DRL4Sec papers (2018-2025), we quantify the prevalence of each pitfall and find an average of over five pitfalls per paper. We demonstrate the practical impact of these pitfalls using controlled experiments in (i) autonomous cyber defense, (ii) adversarial malware creation, and (iii) web security testing environments. Finally, we provide actionable recommendations for each pitfall to support the development of more rigorous and deployable DRL-based security systems. △ Less

Submitted 22 June, 2026; v1 submitted 9 February, 2026; originally announced February 2026.

Comments: Accepted at USENIX Security 2026

ChemPro: A Progressive Chemistry Benchmark for Large Language Models

Authors: Aaditya Baranwal, Shruti Vyas

Abstract: We introduce ChemPro, a progressive benchmark with 4100 natural language question-answer pairs in Chemistry, across 4 coherent sections of difficulty designed to assess the proficiency of Large Language Models (LLMs) in a broad spectrum of general chemistry topics. We include Multiple Choice Questions and Numerical Questions spread across fine-grained information recall, long-horizon reasoning, mu… ▽ More We introduce ChemPro, a progressive benchmark with 4100 natural language question-answer pairs in Chemistry, across 4 coherent sections of difficulty designed to assess the proficiency of Large Language Models (LLMs) in a broad spectrum of general chemistry topics. We include Multiple Choice Questions and Numerical Questions spread across fine-grained information recall, long-horizon reasoning, multi-concept questions, problem-solving with nuanced articulation, and straightforward questions in a balanced ratio, effectively covering Bio-Chemistry, Inorganic-Chemistry, Organic-Chemistry and Physical-Chemistry. ChemPro is carefully designed analogous to a student's academic evaluation for basic to high-school chemistry. A gradual increase in the question difficulty rigorously tests the ability of LLMs to progress from solving basic problems to solving more sophisticated challenges. We evaluate 45+7 state-of-the-art LLMs, spanning both open-source and proprietary variants, and our analysis reveals that while LLMs perform well on basic chemistry questions, their accuracy declines with different types and levels of complexity. These findings highlight the critical limitations of LLMs in general scientific reasoning and understanding and point towards understudied dimensions of difficulty, emphasizing the need for more robust methodologies to improve LLMs. △ Less

Submitted 20 April, 2026; v1 submitted 3 February, 2026; originally announced February 2026.

Comments: Accepted at Artificial Intelligence Chemistry Journal

ACM Class: I.2.7; I.2.0; J.2

Journal ref: Artif. Intell. Chem. 4(1), 100118 (2026)

Quadrupeds for Planetary Exploration: Field Testing Control Algorithms on an Active Volcano

Authors: Shubham Vyas, Franek Stark, Rohit Kumar, Hannah Isermann, Jonas Haack, Mihaela Popescu, Jakob Middelberg, Dennis Mronga, Frank Kirchner

Abstract: Missions such as the Ingenuity helicopter have shown the advantages of using novel locomotion modes to increase the scientific return of planetary exploration missions. Legged robots can further expand the reach and capability of future planetary missions by traversing more difficult terrain than wheeled rovers, such as jumping over cracks on the ground or traversing rugged terrain with boulders.… ▽ More Missions such as the Ingenuity helicopter have shown the advantages of using novel locomotion modes to increase the scientific return of planetary exploration missions. Legged robots can further expand the reach and capability of future planetary missions by traversing more difficult terrain than wheeled rovers, such as jumping over cracks on the ground or traversing rugged terrain with boulders. To develop and test algorithms for using quadruped robots, the AAPLE project was carried out at DFKI. As part of the project, we conducted a series of field experiments on the Volcano on the Aeolian island of Vulcano, an active stratovolcano near Sicily, Italy. The experiments focused on validating newly developed state-of-the-art adaptive optimal control algorithms for quadrupedal locomotion in a high-fidelity analog environment for Lunar and Martian surfaces. This paper presents the technical approach, test plan, software architecture, field deployment strategy, and evaluation results from the Vulcano campaign. △ Less

Submitted 21 October, 2025; originally announced October 2025.

Comments: Presented at 18th Symposium on Advanced Space Technologies in Robotics and Automation (ASTRA)

Journal ref: 18th Symposium on Advanced Space Technologies in Robotics and Automation (ASTRA), 2025

An adaptive hierarchical control framework for quadrupedal robots in planetary exploration

Authors: Franek Stark, Rohit Kumar, Shubham Vyas, Hannah Isermann, Jonas Haack, Mihaela Popescu, Jakob Middelberg, Dennis Mronga, Frank Kirchner

Abstract: Planetary exploration missions require robots capable of navigating extreme and unknown environments. While wheeled rovers have dominated past missions, their mobility is limited to traversable surfaces. Legged robots, especially quadrupeds, can overcome these limitations by handling uneven, obstacle-rich, and deformable terrains. However, deploying such robots in unknown conditions is challenging… ▽ More Planetary exploration missions require robots capable of navigating extreme and unknown environments. While wheeled rovers have dominated past missions, their mobility is limited to traversable surfaces. Legged robots, especially quadrupeds, can overcome these limitations by handling uneven, obstacle-rich, and deformable terrains. However, deploying such robots in unknown conditions is challenging due to the need for environment-specific control, which is infeasible when terrain and robot parameters are uncertain. This work presents a modular control framework that combines model-based dynamic control with online model adaptation and adaptive footstep planning to address uncertainties in both robot and terrain properties. The framework includes state estimation for quadrupeds with and without contact sensing, supports runtime reconfiguration, and is integrated into ROS 2 with open-source availability. Its performance was validated on two quadruped platforms, multiple hardware architectures, and in a volcano field test, where the robot walked over 700 m. △ Less

Submitted 20 October, 2025; originally announced October 2025.

Comments: Presented at 18th Symposium on Advanced Space Technologies in Robotics and Automation (ASTRA)

SynSpill: Improved Industrial Spill Detection With Synthetic Data

Authors: Aaditya Baranwal, Abdul Mueez, Jason Voelker, Guneet Bhatia, Shruti Vyas

Abstract: Large-scale Vision-Language Models (VLMs) have transformed general-purpose visual recognition through strong zero-shot capabilities. However, their performance degrades significantly in niche, safety-critical domains such as industrial spill detection, where hazardous events are rare, sensitive, and difficult to annotate. This scarcity -- driven by privacy concerns, data sensitivity, and the infre… ▽ More Large-scale Vision-Language Models (VLMs) have transformed general-purpose visual recognition through strong zero-shot capabilities. However, their performance degrades significantly in niche, safety-critical domains such as industrial spill detection, where hazardous events are rare, sensitive, and difficult to annotate. This scarcity -- driven by privacy concerns, data sensitivity, and the infrequency of real incidents -- renders conventional fine-tuning of detectors infeasible for most industrial settings. We address this challenge by introducing a scalable framework centered on a high-quality synthetic data generation pipeline. We demonstrate that this synthetic corpus enables effective Parameter-Efficient Fine-Tuning (PEFT) of VLMs and substantially boosts the performance of state-of-the-art object detectors such as YOLO and DETR. Notably, in the absence of synthetic data (SynSpill dataset), VLMs still generalize better to unseen spill scenarios than these detectors. When SynSpill is used, both VLMs and detectors achieve marked improvements, with their performance becoming comparable. Our results underscore that high-fidelity synthetic data is a powerful means to bridge the domain gap in safety-critical applications. The combination of synthetic generation and lightweight adaptation offers a cost-effective, scalable pathway for deploying vision systems in industrial environments where real data is scarce/impractical to obtain. Project Page: https://synspill.vercel.app △ Less

Submitted 13 August, 2025; originally announced August 2025.

Comments: Accepted at ICCV (VISION'25 Workshop) 2025

Journal ref: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 1425-1434

Re:Verse -- Can Your VLM Read a Manga?

Authors: Aaditya Baranwal, Madhav Kataria, Naitik Agrawal, Yogesh S Rawat, Shruti Vyas

Abstract: Current Vision Language Models (VLMs) demonstrate a critical gap between surface-level recognition and deep narrative reasoning when processing sequential visual storytelling. Through a comprehensive investigation of manga narrative understanding, we reveal that while recent large multimodal models excel at individual panel interpretation, they systematically fail at temporal causality and cross-p… ▽ More Current Vision Language Models (VLMs) demonstrate a critical gap between surface-level recognition and deep narrative reasoning when processing sequential visual storytelling. Through a comprehensive investigation of manga narrative understanding, we reveal that while recent large multimodal models excel at individual panel interpretation, they systematically fail at temporal causality and cross-panel cohesion, core requirements for coherent story comprehension. We introduce a novel evaluation framework that combines fine-grained multimodal annotation, cross-modal embedding analysis, and retrieval-augmented assessment to systematically characterize these limitations. Our methodology includes (i) a rigorous annotation protocol linking visual elements to narrative structure through aligned light novel text, (ii) comprehensive evaluation across multiple reasoning paradigms, including direct inference and retrieval-augmented generation, and (iii) cross-modal similarity analysis revealing fundamental misalignments in current VLMs' joint representations. Applying this framework to Re:Zero manga across 11 chapters with 308 annotated panels, we conduct the first systematic study of long-form narrative understanding in VLMs through three core evaluation axes: generative storytelling, contextual dialogue grounding, and temporal reasoning. Our findings demonstrate that current models lack genuine story-level intelligence, struggling particularly with non-linear narratives, character consistency, and causal inference across extended sequences. This work establishes both the foundation and practical methodology for evaluating narrative intelligence, while providing actionable insights into the capability of deep sequential understanding of Discrete Visual Narratives beyond basic recognition in Multimodal Models. Project Page: https://re-verse.vercel.app △ Less

Submitted 18 August, 2025; v1 submitted 11 August, 2025; originally announced August 2025.

Comments: Accepted (oral) at ICCV (AISTORY Workshop) 2025

Journal ref: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 3820-3830

iSafetyBench: A video-language benchmark for safety in industrial environment

Authors: Raiyaan Abdullah, Yogesh Singh Rawat, Shruti Vyas

Abstract: Recent advances in vision-language models (VLMs) have enabled impressive generalization across diverse video understanding tasks under zero-shot settings. However, their capabilities in high-stakes industrial domains-where recognizing both routine operations and safety-critical anomalies is essential-remain largely underexplored. To address this gap, we introduce iSafetyBench, a new video-language… ▽ More Recent advances in vision-language models (VLMs) have enabled impressive generalization across diverse video understanding tasks under zero-shot settings. However, their capabilities in high-stakes industrial domains-where recognizing both routine operations and safety-critical anomalies is essential-remain largely underexplored. To address this gap, we introduce iSafetyBench, a new video-language benchmark specifically designed to evaluate model performance in industrial environments across both normal and hazardous scenarios. iSafetyBench comprises 1,100 video clips sourced from real-world industrial settings, annotated with open-vocabulary, multi-label action tags spanning 98 routine and 67 hazardous action categories. Each clip is paired with multiple-choice questions for both single-label and multi-label evaluation, enabling fine-grained assessment of VLMs in both standard and safety-critical contexts. We evaluate eight state-of-the-art video-language models under zero-shot conditions. Despite their strong performance on existing video benchmarks, these models struggle with iSafetyBench-particularly in recognizing hazardous activities and in multi-label scenarios. Our results reveal significant performance gaps, underscoring the need for more robust, safety-aware multimodal models for industrial applications. iSafetyBench provides a first-of-its-kind testbed to drive progress in this direction. The dataset is available at: https://github.com/iSafetyBench/data. △ Less

Submitted 13 August, 2025; v1 submitted 1 August, 2025; originally announced August 2025.

Comments: Accepted to VISION'25 - ICCV 2025 workshop

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning

Authors: Sanyam Vyas, Alberto Caron, Chris Hicks, Pete Burnap, Vasilios Mavroudis

Abstract: Deep Reinforcement Learning (DRL) systems are increasingly used in safety-critical applications, yet their security remains severely underexplored. This work investigates backdoor attacks, which implant hidden triggers that cause malicious actions only when specific inputs appear in the observation space. Existing DRL backdoor research focuses solely on training-time attacks requiring unrealistic… ▽ More Deep Reinforcement Learning (DRL) systems are increasingly used in safety-critical applications, yet their security remains severely underexplored. This work investigates backdoor attacks, which implant hidden triggers that cause malicious actions only when specific inputs appear in the observation space. Existing DRL backdoor research focuses solely on training-time attacks requiring unrealistic access to the training pipeline. In contrast, we reveal critical vulnerabilities across the DRL supply chain where backdoors can be embedded with significantly reduced adversarial privileges. We introduce two novel attacks: (1) TrojanentRL, which exploits component-level flaws to implant a persistent backdoor that survives full model retraining; and (2) InfrectroRL, a post-training backdoor attack which requires no access to training, validation, nor test data. Empirical and analytical evaluations across six Atari environments show our attacks rival state-of-the-art training-time backdoor attacks while operating under much stricter adversarial constraints. We also demonstrate that InfrectroRL further evades two leading DRL backdoor defenses. These findings challenge the current research focus and highlight the urgent need for robust defenses. △ Less

Submitted 7 July, 2025; originally announced July 2025.

MolVision: Molecular Property Prediction with Vision Language Models

Authors: Deepan Adak, Yogesh Singh Rawat, Shruti Vyas

Abstract: Molecular property prediction is a fundamental task in computational chemistry with critical applications in drug discovery and materials science. While recent works have explored Large Language Models (LLMs) for this task, they primarily rely on textual molecular representations such as SMILES/SELFIES, which can be ambiguous and structurally less informative. In this work, we introduce MolVision,… ▽ More Molecular property prediction is a fundamental task in computational chemistry with critical applications in drug discovery and materials science. While recent works have explored Large Language Models (LLMs) for this task, they primarily rely on textual molecular representations such as SMILES/SELFIES, which can be ambiguous and structurally less informative. In this work, we introduce MolVision, a novel approach that leverages Vision-Language Models (VLMs) by integrating both molecular structure as images and textual descriptions to enhance property prediction. We construct a benchmark spanning ten diverse datasets, covering classification, regression and description tasks. Evaluating nine different VLMs in zero-shot, few-shot, and fine-tuned settings, we find that visual information improves prediction performance, particularly when combined with efficient fine-tuning strategies such as LoRA. Our results reveal that while visual information alone is insufficient, multimodal fusion significantly enhances generalization across molecular properties. Adaptation of vision encoder for molecular images in conjunction with LoRA further improves the performance. The code and data is available at : $\href{https://molvision.github.io/MolVision/}{https://molvision.github.io/MolVision/}$. △ Less

Submitted 4 July, 2025; originally announced July 2025.

Adaptive Model-Base Control of Quadrupeds via Online System Identification using Kalman Filter

Authors: Jonas Haack, Franek Stark, Shubham Vyas, Frank Kirchner, Shivesh Kumar

Abstract: Many real-world applications require legged robots to be able to carry variable payloads. Model-based controllers such as model predictive control (MPC) have become the de facto standard in research for controlling these systems. However, most model-based control architectures use fixed plant models, which limits their applicability to different tasks. In this paper, we present a Kalman filter (KF… ▽ More Many real-world applications require legged robots to be able to carry variable payloads. Model-based controllers such as model predictive control (MPC) have become the de facto standard in research for controlling these systems. However, most model-based control architectures use fixed plant models, which limits their applicability to different tasks. In this paper, we present a Kalman filter (KF) formulation for online identification of the mass and center of mass (COM) of a four-legged robot. We evaluate our method on a quadrupedal robot carrying various payloads and find that it is more robust to strong measurement noise than classical recursive least squares (RLS) methods. Moreover, it improves the tracking performance of the model-based controller with varying payloads when the model parameters are adjusted at runtime. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Comments: 6 pages, 5 figures, 1 table, accepted for IEEE IROS 2025

Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering

Authors: Andres Carofilis, Pradeep Rangappa, Srikanth Madikeri, Shashi Kumar, Sergio Burdisso, Jeena Prakash, Esau Villatoro-Tello, Petr Motlicek, Bidisha Sharma, Kadri Hacioglu, Shankar Venkatesan, Saurabh Vyas, Andreas Stolcke

Abstract: Fine-tuning pretrained ASR models for specific domains is challenging when labeled data is scarce. But unlabeled audio and labeled data from related domains are often available. We propose an incremental semi-supervised learning pipeline that first integrates a small in-domain labeled set and an auxiliary dataset from a closely related domain, achieving a relative improvement of 4% over no auxilia… ▽ More Fine-tuning pretrained ASR models for specific domains is challenging when labeled data is scarce. But unlabeled audio and labeled data from related domains are often available. We propose an incremental semi-supervised learning pipeline that first integrates a small in-domain labeled set and an auxiliary dataset from a closely related domain, achieving a relative improvement of 4% over no auxiliary data. Filtering based on multi-model consensus or named entity recognition (NER) is then applied to select and iteratively refine pseudo-labels, showing slower performance saturation compared to random selection. Evaluated on the multi-domain Wow call center and Fisher English corpora, it outperforms single-step fine-tuning. Consensus-based filtering outperforms other methods, providing up to 22.3% relative improvement on Wow and 24.8% on Fisher over single-step fine-tuning with random selection. NER is the second-best filter, providing competitive performance at a lower computational cost. △ Less

Submitted 5 June, 2025; originally announced June 2025.

Comments: Accepted at Interspeech 2025, Netherlands

Journal ref: Proc. Interspeech 2025, 3618-3622

Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering

Authors: Pradeep Rangappa, Andres Carofilis, Jeena Prakash, Shashi Kumar, Sergio Burdisso, Srikanth Madikeri, Esau Villatoro-Tello, Bidisha Sharma, Petr Motlicek, Kadri Hacioglu, Shankar Venkatesan, Saurabh Vyas, Andreas Stolcke

Abstract: Fine-tuning pretrained ASR models for specific domains is challenging for small organizations with limited labeled data and computational resources. Here, we explore different data selection pipelines and propose a robust approach that improves ASR adaptation by filtering pseudo-labels generated using Whisper (encoder-decoder) and Zipformer (transducer) models. Our approach integrates multiple sel… ▽ More Fine-tuning pretrained ASR models for specific domains is challenging for small organizations with limited labeled data and computational resources. Here, we explore different data selection pipelines and propose a robust approach that improves ASR adaptation by filtering pseudo-labels generated using Whisper (encoder-decoder) and Zipformer (transducer) models. Our approach integrates multiple selection strategies -- including word error rate (WER) prediction, named entity recognition (NER), and character error rate (CER) analysis -- to extract high-quality training segments. We evaluate our method on Whisper and Zipformer using a 7500-hour baseline, comparing it to a CER-based approach relying on hypotheses from three ASR systems. Fine-tuning on 7500 hours of pseudo-labeled call center data achieves 12.3% WER, while our filtering reduces the dataset to 100 hours (1.4%) with similar performance; a similar trend is observed on Fisher English. △ Less

Submitted 4 June, 2025; originally announced June 2025.

Comments: Accepted at Interspeech 2025, Netherlands

Journal ref: Proc. Interspeech 2025, pp. 4928-4932

Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd 'AI Olympics with RealAIGym' Competition

Authors: Felix Wiebe, Niccolò Turcato, Alberto Dalla Libera, Jean Seong Bjorn Choe, Bumkyu Choi, Tim Lukas Faust, Habib Maraqten, Erfan Aghadavoodi, Marco Cali, Alberto Sinigaglia, Giulio Giacomuzzo, Diego Romeres, Jong-kook Kim, Gian Antonio Susto, Shubham Vyas, Dennis Mronga, Boris Belousov, Jan Peters, Frank Kirchner, Shivesh Kumar

Abstract: In the field of robotics many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. In order to get a clear understanding of their individual strengths and weaknesses and their applicability in real world robotic scenarios is it important to benchmark and co… ▽ More In the field of robotics many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. In order to get a clear understanding of their individual strengths and weaknesses and their applicability in real world robotic scenarios is it important to benchmark and compare their performances not only in a simulation but also on real hardware. The '2nd AI Olympics with RealAIGym' competition was held at the IROS 2024 conference to contribute to this cause and evaluate different controllers according to their ability to solve a dynamic control problem on an underactuated double pendulum system with chaotic dynamics. This paper describes the four different RL methods submitted by the participating teams, presents their performance in the swing-up task on a real double pendulum, measured against various criteria, and discusses their transferability from simulation to real hardware and their robustness to external disturbances. △ Less

Submitted 19 March, 2025; originally announced March 2025.

Comments: 8 pages, 7 figures

LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models

Authors: Priyank Pathak, Shyam Marjit, Shruti Vyas, Yogesh S Rawat

Abstract: Visual-language foundation Models (FMs) exhibit remarkable zero-shot generalization across diverse tasks, largely attributed to extensive pre-training on largescale datasets. However, their robustness on low-resolution/pixelated (LR) images, a common challenge in real-world scenarios, remains underexplored. We introduce LR0.FM, a comprehensive benchmark evaluating the impact of low resolution on t… ▽ More Visual-language foundation Models (FMs) exhibit remarkable zero-shot generalization across diverse tasks, largely attributed to extensive pre-training on largescale datasets. However, their robustness on low-resolution/pixelated (LR) images, a common challenge in real-world scenarios, remains underexplored. We introduce LR0.FM, a comprehensive benchmark evaluating the impact of low resolution on the zero-shot classification performance of 10 FM(s) across 66 backbones and 15 datasets. We propose a novel metric, Weighted Aggregated Robustness, to address the limitations of existing metrics and better evaluate model performance across resolutions and datasets. Our key findings show that: (i) model size positively correlates with robustness to resolution degradation, (ii) pre-training dataset quality is more important than its size, and (iii) fine-tuned and higher resolution models are less robust against LR. Our analysis further reveals that the model makes semantically reasonable predictions at LR, and the lack of fine-grained details in input adversely impacts the model's initial layers more than the deeper layers. We use these insights and introduce a simple strategy, LR-TK0, to enhance the robustness of models without compromising their pre-trained weights. We demonstrate the effectiveness of LR-TK0 for robustness against low-resolution across several datasets and its generalization capability across backbones and other approaches. Code is available at https://github.com/shyammarjit/LR0.FM △ Less

Submitted 18 May, 2025; v1 submitted 6 February, 2025; originally announced February 2025.

Comments: Accepted to ICLR 2025

Benchmarking Different QP Formulations and Solvers for Dynamic Quadrupedal Walking

Authors: Franek Stark, Jakob Middelberg, Dennis Mronga, Shubham Vyas, Frank Kirchner

Abstract: Quadratic Programs (QPs) are widely used in the control of walking robots, especially in Model Predictive Control (MPC) and Whole-Body Control (WBC). In both cases, the controller design requires the formulation of a QP and the selection of a suitable QP solver, both requiring considerable time and expertise. While computational performance benchmarks exist for QP solvers, studies comparing optima… ▽ More Quadratic Programs (QPs) are widely used in the control of walking robots, especially in Model Predictive Control (MPC) and Whole-Body Control (WBC). In both cases, the controller design requires the formulation of a QP and the selection of a suitable QP solver, both requiring considerable time and expertise. While computational performance benchmarks exist for QP solvers, studies comparing optimal combinations of computational hardware (HW), QP formulation, and solver performance are lacking. In this work, we compare dense and sparse QP formulations, and multiple solving methods on different HW architectures, focusing on their computational efficiency in dynamic walking of four legged robots using MPC. We introduce the Solve Frequency per Watt (SFPW) as a performance measure to enable a cross hardware comparison of the efficiency of QP solvers. We also benchmark different QP solvers for WBC that we use for trajectory stabilization in quadrupedal walking. As a result, this paper provides recommendations for the selection of QP formulations and solvers for different HW architectures in walking robots and indicates which problems should be devoted the greater technical effort in this domain in future. △ Less

Submitted 3 February, 2025; originally announced February 2025.

Comments: Preprint; Accepted for ICRA 2025

Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points

Authors: Dan Ristea, Shae McFadden, Ezzeldin Shereen, Madeleine Dwyer, Sanyam Vyas, Chris Hicks, Vasilios Mavroudis

Abstract: Security vulnerabilities in software can have severe consequences; however, manual vulnerability detection is costly and does not scale, especially as agentic coding frameworks increase the rate of code production. Over the last decade, a large body of research has applied machine learning machine learning to automate vulnerability detection (ML4AVD), yet self-reported performance on the most popu… ▽ More Security vulnerabilities in software can have severe consequences; however, manual vulnerability detection is costly and does not scale, especially as agentic coding frameworks increase the rate of code production. Over the last decade, a large body of research has applied machine learning machine learning to automate vulnerability detection (ML4AVD), yet self-reported performance on the most popular datasets shows no clear upward trend. The ML4AVD research community has identified several flaws in problem formulations, datasets, and metrics, but these are discussed in isolation, leaving the overarching problems that generate and reinforce these flaws unaddressed. We first systematize the field through a survey of 87 influential works based on their problem formulation, input and detection granularity, target programming languages, evaluation metrics, datasets, and detection approach. Drawing on this corpus and prior empirical work, we identify twelve pain points spanning the ML4AVD pipeline and show that they are self-reinforcing and causally inter-meshed: feedback loops between datasets, formulations, baselines, and metrics perpetuate each other and explain the field's persistent concentration on binary classification of C/C++ vulnerabilities at the function level. Thus, the field optimizes for a narrow and artificial problem that omits vulnerability type prediction, broader language support, and separation of input from detection granularity. We pair each pain point with concrete recommendations to break these loops. Finally, we use AIxCC as a case study to assess how well a recent high-profile effort aligns with these recommendations and reflect on the relevance of ML4AVD in the era of agentic AI. △ Less

Submitted 7 May, 2026; v1 submitted 15 December, 2024; originally announced December 2024.

Univariate Conditional Variational Autoencoder for Morphogenic Patterns Design in Frontal Polymerization-Based Manufacturing

Authors: Qibang Liu, Pengfei Cai, Diab Abueidda, Sagar Vyas, Seid Koric, Rafael Gomez-Bombarelli, Philippe Geubelle

Abstract: Under some initial and boundary conditions, the rapid reaction-thermal diffusion process taking place during frontal polymerization (FP) destabilizes the planar mode of front propagation, leading to spatially varying, complex hierarchical patterns in thermoset polymeric materials. Although modern reaction-diffusion models can predict the patterns resulting from unstable FP, the inverse design of p… ▽ More Under some initial and boundary conditions, the rapid reaction-thermal diffusion process taking place during frontal polymerization (FP) destabilizes the planar mode of front propagation, leading to spatially varying, complex hierarchical patterns in thermoset polymeric materials. Although modern reaction-diffusion models can predict the patterns resulting from unstable FP, the inverse design of patterns, which aims to retrieve process conditions that produce a desired pattern, remains an open challenge due to the non-unique and non-intuitive mapping between process conditions and manufactured patterns. In this work, we propose a probabilistic generative model named univariate conditional variational autoencoder (UcVAE) for the inverse design of hierarchical patterns in FP-based manufacturing. Unlike the cVAE, which encodes both the design space and the design target, the UcVAE encodes only the design space. In the encoder of the UcVAE, the number of training parameters is significantly reduced compared to the cVAE, resulting in a shorter training time while maintaining comparable performance. Given desired pattern images, the trained UcVAE can generate multiple process condition solutions that produce high-fidelity hierarchical patterns. △ Less

Submitted 31 October, 2024; v1 submitted 22 October, 2024; originally announced October 2024.

Model Predictive Parkour Control of a Monoped Hopper in Dynamically Changing Environments

Authors: Maximilian Albracht, Shivesh Kumar, Shubham Vyas, Frank Kirchner

Abstract: A great advantage of legged robots is their ability to operate on particularly difficult and obstructed terrain, which demands dynamic, robust, and precise movements. The study of obstacle courses provides invaluable insights into the challenges legged robots face, offering a controlled environment to assess and enhance their capabilities. Traversing it with a one-legged hopper introduces intricat… ▽ More A great advantage of legged robots is their ability to operate on particularly difficult and obstructed terrain, which demands dynamic, robust, and precise movements. The study of obstacle courses provides invaluable insights into the challenges legged robots face, offering a controlled environment to assess and enhance their capabilities. Traversing it with a one-legged hopper introduces intricate challenges, such as planning over contacts and dealing with flight phases, which necessitates a sophisticated controller. A novel model predictive parkour controller is introduced, that finds an optimal path through a real-time changing obstacle course with mixed integer motion planning. The execution of this optimized path is then achieved through a state machine employing a PD control scheme with feedforward torques, ensuring robust and accurate performance. △ Less

Submitted 26 August, 2024; originally announced August 2024.

Comments: Published in: IEEE Robotics and Automation Letters

Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space

Authors: Sanyam Vyas, Chris Hicks, Vasilios Mavroudis

Abstract: This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers are designed to induce a deviation in the behaviour of a backdoored agent while blending into the expected data distribution to evade detection. Through experimen… ▽ More This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers are designed to induce a deviation in the behaviour of a backdoored agent while blending into the expected data distribution to evade detection. Through experiments conducted in the Atari Breakout environment, we demonstrate the limitations of current sanitisation methods when faced with such triggers and investigate why they present a challenging defence problem. We then evaluate the hypothesis that backdoor triggers might be easier to detect in the neural activation space of the DRL agent's policy network. Our statistical analysis shows that indeed the activation patterns in the agent's policy network are distinct in the presence of a trigger, regardless of how well the trigger is concealed in the environment. Based on this, we propose a new defence approach that uses a classifier trained on clean environment samples and detects abnormal activations. Our results show that even lightweight classifiers can effectively prevent malicious actions with considerable accuracy, indicating the potential of this research direction even against sophisticated adversaries. △ Less

Submitted 21 July, 2024; originally announced July 2024.

Comments: 11 Pages, 12 figures

Journal ref: 2024 IEEE Security and Privacy Workshops (SPW), pp. 76-86, 2024

AUV trajectory optimization with hydrodynamic forces for Icy Moon Exploration

Authors: Lukas Rust, Shubham Vyas, Bilal Wehbe

Abstract: To explore oceans on ice-covered moons in the solar system, energy-efficient Autonomous Underwater Vehicles (AUVs) with long ranges must cover enough distance to record and collect enough data. These usually underactuated vehicles are hard to control when performing tasks such as vertical docking or the inspection of vertical walls. This paper introduces a control strategy for DeepLeng to navigate… ▽ More To explore oceans on ice-covered moons in the solar system, energy-efficient Autonomous Underwater Vehicles (AUVs) with long ranges must cover enough distance to record and collect enough data. These usually underactuated vehicles are hard to control when performing tasks such as vertical docking or the inspection of vertical walls. This paper introduces a control strategy for DeepLeng to navigate in the ice-covered ocean of Jupiter's moon Europa and presents simulation results preceding a discussion on what is further needed for robust control during the mission. △ Less

Submitted 14 June, 2024; originally announced June 2024.

Comments: 7 pages, 8 figures

Journal ref: In 17th Symposium on Advanced Space Technologies in Robotics and Automation, 18-20 October 2023. 2023

Advancing Automatic Photovoltaic Defect Detection using Semi-Supervised Semantic Segmentation of Electroluminescence Images

Authors: Abhishek Jha, Yogesh Rawat, Shruti Vyas

Abstract: Photovoltaic (PV) systems allow us to tap into all abundant solar energy, however they require regular maintenance for high efficiency and to prevent degradation. Traditional manual health check, using Electroluminescence (EL) imaging, is expensive and logistically challenging which makes automated defect detection essential. Current automation approaches require extensive manual expert labeling,… ▽ More Photovoltaic (PV) systems allow us to tap into all abundant solar energy, however they require regular maintenance for high efficiency and to prevent degradation. Traditional manual health check, using Electroluminescence (EL) imaging, is expensive and logistically challenging which makes automated defect detection essential. Current automation approaches require extensive manual expert labeling, which is time-consuming, expensive, and prone to errors. We propose PV-S3 (Photovoltaic-Semi-supervised Semantic Segmentation), a Semi-Supervised Learning approach for semantic segmentation of defects in EL images that reduces reliance on extensive labeling. PV-S3 is an artificial intelligence (AI) model trained using a few labeled images along with numerous unlabeled images. We introduce a novel Semi Cross-Entropy loss function to deal with class imbalance. We evaluate PV-S3 on multiple datasets and demonstrate its effectiveness and adaptability. With merely 20% labeled samples, we achieve an absolute improvement of 9.7% in mean Intersection-over-Union (mIoU), 13.5% in Precision, 29.15% in Recall, and 20.42% in F1-Score over prior state-of-the-art supervised method (which uses 100% labeled samples) on University of Central Florida-Electroluminescence (UCF-EL) dataset (largest dataset available for semantic segmentation of EL images) showing improvement in performance while reducing the annotation costs by 80%. For more details, visit our GitHub repository: https://github.com/abj247/PV-S3. △ Less

Submitted 14 July, 2025; v1 submitted 21 April, 2024; originally announced April 2024.

Comments: 19 pages, 10 figures

Linear Model Predictive Control for a planar free-floating platform: A comparison of binary input constraint formulations

Authors: Franek Stark, Shubham Vyas, Georg Schildbach, Frank Kirchner

Abstract: This work develops a first Model Predictive Control for European Space Agencies 3-dof free-floating platform. The challenges of the platform are the on/off thrusters, which cannot be actuated continuously and which are subject to certain timing constraints. This work compares penalty-term, Linear Complementarity Constraints, and classical Mixed Integer formulations in order to develop a controller… ▽ More This work develops a first Model Predictive Control for European Space Agencies 3-dof free-floating platform. The challenges of the platform are the on/off thrusters, which cannot be actuated continuously and which are subject to certain timing constraints. This work compares penalty-term, Linear Complementarity Constraints, and classical Mixed Integer formulations in order to develop a controller that natively handles binary inputs. Furthermore, linear constraints are proposed which enforce the timing constraints. Only the Mixed Integer formulation turns out to work sufficiently. Hence, this work develops a new Mixed Integer MPC on the decoupled model of the platform. Feasibility analysis and simulation results show that for a short enough prediction horizon, this controller can (sub)optimally stabilize and control the system under consideration of the constraints in real-time. △ Less

Submitted 17 December, 2023; originally announced December 2023.

Comments: 17th Symposium on Advanced Space Technologies in Robotics and Automation (ASTRA 2023)

Semi-supervised Active Learning for Video Action Detection

Authors: Ayush Singh, Aayush J Rana, Akash Kumar, Shruti Vyas, Yogesh Singh Rawat

Abstract: In this work, we focus on label efficient learning for video action detection. We develop a novel semi-supervised active learning approach which utilizes both labeled as well as unlabeled data along with informative sample selection for action detection. Video action detection requires spatio-temporal localization along with classification, which poses several challenges for both active learning i… ▽ More In this work, we focus on label efficient learning for video action detection. We develop a novel semi-supervised active learning approach which utilizes both labeled as well as unlabeled data along with informative sample selection for action detection. Video action detection requires spatio-temporal localization along with classification, which poses several challenges for both active learning informative sample selection as well as semi-supervised learning pseudo label generation. First, we propose NoiseAug, a simple augmentation strategy which effectively selects informative samples for video action detection. Next, we propose fft-attention, a novel technique based on high-pass filtering which enables effective utilization of pseudo label for SSL in video action detection by emphasizing on relevant activity region within a video. We evaluate the proposed approach on three different benchmark datasets, UCF-101-24, JHMDB-21, and Youtube-VOS. First, we demonstrate its effectiveness on video action detection where the proposed approach outperforms prior works in semi-supervised and weakly-supervised learning along with several baseline approaches in both UCF101-24 and JHMDB-21. Next, we also show its effectiveness on Youtube-VOS for video object segmentation demonstrating its generalization capability for other dense prediction tasks in videos. The code and models is publicly available at: \url{https://github.com/AKASH2907/semi-sup-active-learning}. △ Less

Submitted 3 April, 2024; v1 submitted 12 December, 2023; originally announced December 2023.

Comments: AAAI Conference on Artificial Intelligence, Main Technical Track (AAAI), 2024, Code: https://github.com/AKASH2907/semi-sup-active-learning

Histopathological Image Classification and Vulnerability Analysis using Federated Learning

Authors: Sankalp Vyas, Amar Nath Patra, Raj Mani Shukla

Abstract: Healthcare is one of the foremost applications of machine learning (ML). Traditionally, ML models are trained by central servers, which aggregate data from various distributed devices to forecast the results for newly generated data. This is a major concern as models can access sensitive user information, which raises privacy concerns. A federated learning (FL) approach can help address this issue… ▽ More Healthcare is one of the foremost applications of machine learning (ML). Traditionally, ML models are trained by central servers, which aggregate data from various distributed devices to forecast the results for newly generated data. This is a major concern as models can access sensitive user information, which raises privacy concerns. A federated learning (FL) approach can help address this issue: A global model sends its copy to all clients who train these copies, and the clients send the updates (weights) back to it. Over time, the global model improves and becomes more accurate. Data privacy is protected during training, as it is conducted locally on the clients' devices. However, the global model is susceptible to data poisoning. We develop a privacy-preserving FL technique for a skin cancer dataset and show that the model is prone to data poisoning attacks. Ten clients train the model, but one of them intentionally introduces flipped labels as an attack. This reduces the accuracy of the global model. As the percentage of label flipping increases, there is a noticeable decrease in accuracy. We use a stochastic gradient descent optimization algorithm to find the most optimal accuracy for the model. Although FL can protect user privacy for healthcare diagnostics, it is also vulnerable to data poisoning, which must be addressed. △ Less

Submitted 11 October, 2023; originally announced October 2023.

Comments: Accepted in IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

AcroMonk: A Minimalist Underactuated Brachiating Robot

Authors: Mahdi Javadi, Daniel Harnack, Paula Stocco, Shivesh Kumar, Shubham Vyas, Daniel Pizzutilo, Frank Kirchner

Abstract: Brachiation is a dynamic, coordinated swinging maneuver of body and arms used by monkeys and apes to move between branches. As a unique underactuated mode of locomotion, it is interesting to study from a robotics perspective since it can broaden the deployment scenarios for humanoids and animaloids. While several brachiating robots of varying complexity have been proposed in the past, this paper p… ▽ More Brachiation is a dynamic, coordinated swinging maneuver of body and arms used by monkeys and apes to move between branches. As a unique underactuated mode of locomotion, it is interesting to study from a robotics perspective since it can broaden the deployment scenarios for humanoids and animaloids. While several brachiating robots of varying complexity have been proposed in the past, this paper presents the simplest possible prototype of a brachiation robot, using only a single actuator and unactuated grippers. The novel passive gripper design allows it to snap on and release from monkey bars, while guaranteeing well defined start and end poses of the swing. The brachiation behavior is realized in three different ways, using trajectory optimization via direct collocation and stabilization by a model-based time-varying linear quadratic regulator (TVLQR) or model-free proportional derivative (PD) control, as well as by a reinforcement learning (RL) based control policy. The three control schemes are compared in terms of robustness to disturbances, mass uncertainty, and energy consumption. The system design and controllers have been open-sourced. Due to its minimal and open design, the system can serve as a canonical underactuated platform for education and research. △ Less

Submitted 15 May, 2023; originally announced May 2023.

Comments: The open-source implementation is available at https://github.com/dfki-ric-underactuated-lab/acromonk and a video demonstration of the experiments can be accessed at https://youtu.be/FIcDNtJo9Jc}

Journal ref: journal={IEEE Robotics and Automation Letters}, year={2023}, volume={8}, number={6}, pages={3637-3644}

Automated Cyber Defence: A Review

Authors: Sanyam Vyas, John Hannay, Andrew Bolton, Professor Pete Burnap

Abstract: Within recent times, cybercriminals have curated a variety of organised and resolute cyber attacks within a range of cyber systems, leading to consequential ramifications to private and governmental institutions. Current security-based automation and orchestrations focus on automating fixed purpose and hard-coded solutions, which are easily surpassed by modern-day cyber attacks. Research within Au… ▽ More Within recent times, cybercriminals have curated a variety of organised and resolute cyber attacks within a range of cyber systems, leading to consequential ramifications to private and governmental institutions. Current security-based automation and orchestrations focus on automating fixed purpose and hard-coded solutions, which are easily surpassed by modern-day cyber attacks. Research within Automated Cyber Defence will allow the development and enabling intelligence response by autonomously defending networked systems through sequential decision-making agents. This article comprehensively elaborates the developments within Automated Cyber Defence through a requirement analysis divided into two sub-areas, namely, automated defence and attack agents and Autonomous Cyber Operation (ACO) Gyms. The requirement analysis allows the comparison of automated agents and highlights the importance of ACO Gyms for their continual development. The requirement analysis is also used to critique ACO Gyms with an overall aim to develop them for deploying automated agents within real-world networked systems. Relevant future challenges were addressed from the overall analysis to accelerate development within the area of Automated Cyber Defence. △ Less

Submitted 8 March, 2023; originally announced March 2023.

Trajectory Optimization and Following for a Three Degrees of Freedom Overactuated Floating Platform

Authors: Anton Bredenbeck, Shubham Vyas, Martin Zwick, Dorit Borrmann, Miguel Olivares-Mendez, Andreas Nüchter

Abstract: Space robotics applications, such as Active Space Debris Removal (ASDR), require representative testing before launch. A commonly used approach to emulate the microgravity environment in space is air-bearing based platforms on flat-floors, such as the European Space Agency's Orbital Robotics and GNC Lab (ORGL). This work proposes a control architecture for a floating platform at the ORGL, equipped… ▽ More Space robotics applications, such as Active Space Debris Removal (ASDR), require representative testing before launch. A commonly used approach to emulate the microgravity environment in space is air-bearing based platforms on flat-floors, such as the European Space Agency's Orbital Robotics and GNC Lab (ORGL). This work proposes a control architecture for a floating platform at the ORGL, equipped with eight solenoid-valve-based thrusters and one reaction wheel. The control architecture consists of two main components: a trajectory planner that finds optimal trajectories connecting two states and a trajectory follower that follows any physically feasible trajectory. The controller is first evaluated within an introduced simulation, achieving a 100 % success rate at finding and following trajectories to the origin within a Monte-Carlo test. Individual trajectories are also successfully followed by the physical system. In this work, we showcase the ability of the controller to reject disturbances and follow a straight-line trajectory within tens of centimeters. △ Less

Submitted 21 July, 2022; originally announced July 2022.

Comments: Accepted to IROS2022, code at https://gitlab.com/anton.bredenbeck/ff-trajectories

GAMa: Cross-view Video Geo-localization

Authors: Shruti Vyas, Chen Chen, Mubarak Shah

Abstract: The existing work in cross-view geo-localization is based on images where a ground panorama is matched to an aerial image. In this work, we focus on ground videos instead of images which provides additional contextual cues which are important for this task. There are no existing datasets for this problem, therefore we propose GAMa dataset, a large-scale dataset with ground videos and corresponding… ▽ More The existing work in cross-view geo-localization is based on images where a ground panorama is matched to an aerial image. In this work, we focus on ground videos instead of images which provides additional contextual cues which are important for this task. There are no existing datasets for this problem, therefore we propose GAMa dataset, a large-scale dataset with ground videos and corresponding aerial images. We also propose a novel approach to solve this problem. At clip-level, a short video clip is matched with corresponding aerial image and is later used to get video-level geo-localization of a long video. Moreover, we propose a hierarchical approach to further improve the clip-level geolocalization. It is a challenging dataset, unaligned and limited field of view, and our proposed method achieves a Top-1 recall rate of 19.4% and 45.1% @1.0mile. Code and dataset are available at following link: https://github.com/svyas23/GAMa. △ Less

Submitted 6 July, 2022; originally announced July 2022.

Journal ref: ECCV 2022

Robustness Analysis of Video-Language Models Against Visual and Language Perturbations

Authors: Madeline C. Schiappa, Shruti Vyas, Hamid Palangi, Yogesh S. Rawat, Vibhav Vineet

Abstract: Joint visual and language modeling on large-scale datasets has recently shown good progress in multi-modal tasks when compared to single modal learning. However, robustness of these approaches against real-world perturbations has not been studied. In this work, we perform the first extensive robustness study of video-language models against various real-world perturbations. We focus on text-to-vid… ▽ More Joint visual and language modeling on large-scale datasets has recently shown good progress in multi-modal tasks when compared to single modal learning. However, robustness of these approaches against real-world perturbations has not been studied. In this work, we perform the first extensive robustness study of video-language models against various real-world perturbations. We focus on text-to-video retrieval and propose two large-scale benchmark datasets, MSRVTT-P and YouCook2-P, which utilize 90 different visual and 35 different text perturbations. The study reveals some interesting initial findings from the studied models: 1) models are generally more susceptible when only video is perturbed as opposed to when only text is perturbed, 2) models that are pre-trained are more robust than those trained from scratch, 3) models attend more to scene and objects rather than motion and action. We hope this study will serve as a benchmark and guide future research in robust video-language learning. The benchmark introduced in this study along with the code and datasets is available at https://bit.ly/3CNOly4. △ Less

Submitted 18 July, 2023; v1 submitted 5 July, 2022; originally announced July 2022.

Comments: NeurIPS 2022 Datasets and Benchmarks Track. This projects webpage is located at https://bit.ly/3CNOly4

Journal ref: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (2022)

Large-scale Robustness Analysis of Video Action Recognition Models

Authors: Madeline Chantry Schiappa, Naman Biyani, Prudvi Kamtam, Shruti Vyas, Hamid Palangi, Vibhav Vineet, Yogesh Rawat

Abstract: We have seen a great progress in video action recognition in recent years. There are several models based on convolutional neural network (CNN) and some recent transformer based approaches which provide top performance on existing benchmarks. In this work, we perform a large-scale robustness analysis of these existing models for video action recognition. We focus on robustness against real-world d… ▽ More We have seen a great progress in video action recognition in recent years. There are several models based on convolutional neural network (CNN) and some recent transformer based approaches which provide top performance on existing benchmarks. In this work, we perform a large-scale robustness analysis of these existing models for video action recognition. We focus on robustness against real-world distribution shift perturbations instead of adversarial perturbations. We propose four different benchmark datasets, HMDB51-P, UCF101-P, Kinetics400-P, and SSv2-P to perform this analysis. We study robustness of six state-of-the-art action recognition models against 90 different perturbations. The study reveals some interesting findings, 1) transformer based models are consistently more robust compared to CNN based models, 2) Pretraining improves robustness for Transformer based models more than CNN based models, and 3) All of the studied models are robust to temporal perturbations for all datasets but SSv2; suggesting the importance of temporal information for action recognition varies based on the dataset and activities. Next, we study the role of augmentations in model robustness and present a real-world dataset, UCF101-DS, which contains realistic distribution shifts, to further validate some of these findings. We believe this study will serve as a benchmark for future research in robust video action recognition. △ Less

Submitted 7 April, 2023; v1 submitted 4 July, 2022; originally announced July 2022.

Comments: Accepted in 2023 Conference on Computer Vision and Pattern Recognition (CVPR)

Finding and Following Optimal Trajectories for an Overactuated Floating Robotic Platform

Authors: Anton Bredenbeck, Shubham Vyas, Willem Suter, Martin Zwick, Dorit Borrmann, Miguel Olivares-Mendez, Andreas Nüchter

Abstract: The recent increase in yearly spacecraft launches and the high number of planned launches have raised questions about maintaining accessibility to space for all interested parties. A key to sustaining the future of space-flight is the ability to service malfunctioning - and actively remove dysfunctional spacecraft from orbit. Robotic platforms that autonomously perform these tasks are a topic of o… ▽ More The recent increase in yearly spacecraft launches and the high number of planned launches have raised questions about maintaining accessibility to space for all interested parties. A key to sustaining the future of space-flight is the ability to service malfunctioning - and actively remove dysfunctional spacecraft from orbit. Robotic platforms that autonomously perform these tasks are a topic of ongoing research and thus must undergo thorough testing before launch. For representative system-level testing, the European Space Agency (ESA) uses, among other things, the Orbital Robotics and GNC Lab (ORGL), a flat-floor facility where air-bearing based platforms exhibit free-floating behavior in three Degrees of Freedom (DoF). This work introduces a representative simulation of a free-floating platform in the testing environment and a software framework for controller development. Finally, this work proposes a controller within that framework for finding and following optimal trajectories between arbitrary states, which is evaluated in simulation and reality. △ Less

Submitted 19 July, 2022; v1 submitted 8 June, 2022; originally announced June 2022.

Comments: 16th Symposium on Advanced Space Technologies in Robotics and Automation 2022

Forecasting Solar Power Generation on the basis of Predictive and Corrective Maintenance Activities

Authors: Soham Vyas, Yuvraj Goyal, Neel Bhatt, Sanskar Bhuwania, Hardik Patel, Shakti Mishra, Brijesh Tripathi

Abstract: Solar energy forecasting has seen tremendous growth in the last decade using historical time series collected from a weather station, such as weather variables wind speed and direction, solar radiance, and temperature. It helps in the overall management of solar power plants. However, the solar power plant regularly requires preventive and corrective maintenance activities that further impact ener… ▽ More Solar energy forecasting has seen tremendous growth in the last decade using historical time series collected from a weather station, such as weather variables wind speed and direction, solar radiance, and temperature. It helps in the overall management of solar power plants. However, the solar power plant regularly requires preventive and corrective maintenance activities that further impact energy production. This paper presents a novel work for forecasting solar power energy production based on maintenance activities, problems observed at a power plant, and weather data. The results accomplished on the datasets obtained from the 1MW solar power plant of PDEU (our university) that has generated data set with 13 columns as daily entries from 2012 to 2020. There are 12 structured columns and one unstructured column with manual text entries about different maintenance activities, problems observed, and weather conditions daily. The unstructured column is used to create a new feature column vector using Hash Map, flag words, and stop words. The final dataset comprises five important feature vector columns based on correlation and causality analysis. △ Less

Submitted 17 May, 2022; originally announced May 2022.

Video Action Detection: Analysing Limitations and Challenges

Authors: Rajat Modi, Aayush Jung Rana, Akash Kumar, Praveen Tirupattur, Shruti Vyas, Yogesh Singh Rawat, Mubarak Shah

Abstract: Beyond possessing large enough size to feed data hungry machines (eg, transformers), what attributes measure the quality of a dataset? Assuming that the definitions of such attributes do exist, how do we quantify among their relative existences? Our work attempts to explore these questions for video action detection. The task aims to spatio-temporally localize an actor and assign a relevant action… ▽ More Beyond possessing large enough size to feed data hungry machines (eg, transformers), what attributes measure the quality of a dataset? Assuming that the definitions of such attributes do exist, how do we quantify among their relative existences? Our work attempts to explore these questions for video action detection. The task aims to spatio-temporally localize an actor and assign a relevant action class. We first analyze the existing datasets on video action detection and discuss their limitations. Next, we propose a new dataset, Multi Actor Multi Action (MAMA) which overcomes these limitations and is more suitable for real world applications. In addition, we perform a biasness study which analyzes a key property differentiating videos from static images: the temporal aspect. This reveals if the actions in these datasets really need the motion information of an actor, or whether they predict the occurrence of an action even by looking at a single frame. Finally, we investigate the widely held assumptions on the importance of temporal ordering: is temporal ordering important for detecting these actions? Such extreme experiments show existence of biases which have managed to creep into existing methods inspite of careful modeling. △ Less

Submitted 16 April, 2022; originally announced April 2022.

Comments: CVPRW'22

LARNet: Latent Action Representation for Human Action Synthesis

Authors: Naman Biyani, Aayush J Rana, Shruti Vyas, Yogesh S Rawat

Abstract: We present LARNet, a novel end-to-end approach for generating human action videos. A joint generative modeling of appearance and dynamics to synthesize a video is very challenging and therefore recent works in video synthesis have proposed to decompose these two factors. However, these methods require a driving video to model the video dynamics. In this work, we propose a generative approach inste… ▽ More We present LARNet, a novel end-to-end approach for generating human action videos. A joint generative modeling of appearance and dynamics to synthesize a video is very challenging and therefore recent works in video synthesis have proposed to decompose these two factors. However, these methods require a driving video to model the video dynamics. In this work, we propose a generative approach instead, which explicitly learns action dynamics in latent space avoiding the need of a driving video during inference. The generated action dynamics is integrated with the appearance using a recurrent hierarchical structure which induces motion at different scales to focus on both coarse as well as fine level action details. In addition, we propose a novel mix-adversarial loss function which aims at improving the temporal coherency of synthesized videos. We evaluate the proposed approach on four real-world human action datasets demonstrating the effectiveness of the proposed approach in generating human actions. Code available at https://github.com/aayushjr/larnet. △ Less

Submitted 26 October, 2021; v1 submitted 21 October, 2021; originally announced October 2021.

Comments: British Machine Vision Conference (BMVC) 2021

Pose-guided Generative Adversarial Net for Novel View Action Synthesis

Authors: Xianhang Li, Junhao Zhang, Kunchang Li, Shruti Vyas, Yogesh S Rawat

Abstract: We focus on the problem of novel-view human action synthesis. Given an action video, the goal is to generate the same action from an unseen viewpoint. Naturally, novel view video synthesis is more challenging than image synthesis. It requires the synthesis of a sequence of realistic frames with temporal coherency. Besides, transferring the different actions to a novel target view requires awarenes… ▽ More We focus on the problem of novel-view human action synthesis. Given an action video, the goal is to generate the same action from an unseen viewpoint. Naturally, novel view video synthesis is more challenging than image synthesis. It requires the synthesis of a sequence of realistic frames with temporal coherency. Besides, transferring the different actions to a novel target view requires awareness of action category and viewpoint change simultaneously. To address these challenges, we propose a novel framework named Pose-guided Action Separable Generative Adversarial Net (PAS-GAN), which utilizes pose to alleviate the difficulty of this task. First, we propose a recurrent pose-transformation module which transforms actions from the source view to the target view and generates novel view pose sequence in 2D coordinate space. Second, a well-transformed pose sequence enables us to separatethe action and background in the target view. We employ a novel local-global spatial transformation module to effectively generate sequential video features in the target view using these action and background features. Finally, the generated video features are used to synthesize human action with the help of a 3D decoder. Moreover, to focus on dynamic action in the video, we propose a novel multi-scale action-separable loss which further improves the video quality. We conduct extensive experiments on two large-scale multi-view human action datasets, NTU-RGBD and PKU-MMD, demonstrating the effectiveness of PAS-GAN which outperforms existing approaches. △ Less

Submitted 8 December, 2021; v1 submitted 15 October, 2021; originally announced October 2021.

Comments: Accepted by WACV2022

NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labels

Authors: Mohit Sharma, Raj Patra, Harshal Desai, Shruti Vyas, Yogesh Rawat, Rajiv Ratn Shah

Abstract: Deep learning has shown remarkable progress in a wide range of problems. However, efficient training of such models requires large-scale datasets, and getting annotations for such datasets can be challenging and costly. In this work, we explore the use of user-generated freely available labels from web videos for video understanding. We create a benchmark dataset consisting of around 2 million vid… ▽ More Deep learning has shown remarkable progress in a wide range of problems. However, efficient training of such models requires large-scale datasets, and getting annotations for such datasets can be challenging and costly. In this work, we explore the use of user-generated freely available labels from web videos for video understanding. We create a benchmark dataset consisting of around 2 million videos with associated user-generated annotations and other meta information. We utilize the collected dataset for action classification and demonstrate its usefulness with existing small-scale annotated datasets, UCF101 and HMDB51. We study different loss functions and two pretraining strategies, simple and self-supervised learning. We also show how a network pretrained on the proposed dataset can help against video corruption and label noise in downstream datasets. We present this as a benchmark dataset in noisy learning for video understanding. The dataset, code, and trained models will be publicly available for future research. △ Less

Submitted 13 October, 2021; originally announced October 2021.

Comments: Accepted at ACM Multimedia Asia 2021

TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videos

Authors: Praveen Tirupattur, Aayush J Rana, Tushar Sangam, Shruti Vyas, Yogesh S Rawat, Mubarak Shah

Abstract: This paper summarizes the TinyAction challenge which was organized in ActivityNet workshop at CVPR 2021. This challenge focuses on recognizing real-world low-resolution activities present in videos. Action recognition task is currently focused around classifying the actions from high-quality videos where the actors and the action is clearly visible. While various approaches have been shown effecti… ▽ More This paper summarizes the TinyAction challenge which was organized in ActivityNet workshop at CVPR 2021. This challenge focuses on recognizing real-world low-resolution activities present in videos. Action recognition task is currently focused around classifying the actions from high-quality videos where the actors and the action is clearly visible. While various approaches have been shown effective for recognition task in recent works, they often do not deal with videos of lower resolution where the action is happening in a tiny region. However, many real world security videos often have the actual action captured in a small resolution, making action recognition in a tiny region a challenging task. In this work, we propose a benchmark dataset, TinyVIRAT-v2, which is comprised of naturally occuring low-resolution actions. This is an extension of the TinyVIRAT dataset and consists of actions with multiple labels. The videos are extracted from security videos which makes them realistic and more challenging. We use current state-of-the-art action recognition methods on the dataset as a benchmark, and propose the TinyAction Challenge. △ Less

Submitted 23 July, 2021; originally announced July 2021.

Comments: 8 pages. arXiv admin note: text overlap with arXiv:2007.07355

Novel View Video Prediction Using a Dual Representation

Authors: Sarah Shiraz, Krishna Regmi, Shruti Vyas, Yogesh S. Rawat, Mubarak Shah

Abstract: We address the problem of novel view video prediction; given a set of input video clips from a single/multiple views, our network is able to predict the video from a novel view. The proposed approach does not require any priors and is able to predict the video from wider angular distances, upto 45 degree, as compared to the recent studies predicting small variations in viewpoint. Moreover, our met… ▽ More We address the problem of novel view video prediction; given a set of input video clips from a single/multiple views, our network is able to predict the video from a novel view. The proposed approach does not require any priors and is able to predict the video from wider angular distances, upto 45 degree, as compared to the recent studies predicting small variations in viewpoint. Moreover, our method relies only onRGB frames to learn a dual representation which is used to generate the video from a novel viewpoint. The dual representation encompasses a view-dependent and a global representation which incorporates complementary details to enable novel view video prediction. We demonstrate the effectiveness of our framework on two real world datasets: NTU-RGB+D and CMU Panoptic. A comparison with the State-of-the-art novel view video prediction methods shows an improvement of 26.1% in SSIM, 13.6% in PSNR, and 60% inFVD scores without using explicit priors from target views. △ Less

Submitted 7 June, 2021; originally announced June 2021.

Comments: Accepted in ICIP 2021

Multilingual and code-switching ASR challenges for low resource Indian languages

Authors: Anuj Diwan, Rakesh Vaideeswaran, Sanket Shah, Ankita Singh, Srinivasa Raghavan, Shreya Khare, Vinit Unni, Saurabh Vyas, Akash Rajpuria, Chiranjeevi Yarra, Ashish Mittal, Prasanta Kumar Ghosh, Preethi Jyothi, Kalika Bali, Vivek Seshadri, Sunayana Sitaram, Samarth Bharadwaj, Jai Nanavati, Raoul Nanavati, Karthik Sankaranarayanan, Tejaswi Seeram, Basil Abraham

Abstract: Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking advantage of low amounts of labeled corpora in multiple languages. With multilingualism becoming common in today's world, there has been increasing interest in code-switching ASR as well. In code-switching, multiple language… ▽ More Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking advantage of low amounts of labeled corpora in multiple languages. With multilingualism becoming common in today's world, there has been increasing interest in code-switching ASR as well. In code-switching, multiple languages are freely interchanged within a single sentence or between sentences. The success of low-resource multilingual and code-switching ASR often depends on the variety of languages in terms of their acoustics, linguistic characteristics as well as the amount of data available and how these are carefully considered in building the ASR system. In this challenge, we would like to focus on building multilingual and code-switching ASR systems through two different subtasks related to a total of seven Indian languages, namely Hindi, Marathi, Odia, Tamil, Telugu, Gujarati and Bengali. For this purpose, we provide a total of ~600 hours of transcribed speech data, comprising train and test sets, in these languages including two code-switched language pairs, Hindi-English and Bengali-English. We also provide a baseline recipe for both the tasks with a WER of 30.73% and 32.45% on the test sets of multilingual and code-switching subtasks, respectively. △ Less

Submitted 31 March, 2021; originally announced April 2021.

Comments: 6 pages

View-invariant action recognition

Authors: Yogesh S Rawat, Shruti Vyas

Abstract: Human action recognition is an important problem in computer vision. It has a wide range of applications in surveillance, human-computer interaction, augmented reality, video indexing, and retrieval. The varying pattern of spatio-temporal appearance generated by human action is key for identifying the performed action. We have seen a lot of research exploring this dynamics of spatio-temporal appea… ▽ More Human action recognition is an important problem in computer vision. It has a wide range of applications in surveillance, human-computer interaction, augmented reality, video indexing, and retrieval. The varying pattern of spatio-temporal appearance generated by human action is key for identifying the performed action. We have seen a lot of research exploring this dynamics of spatio-temporal appearance for learning a visual representation of human actions. However, most of the research in action recognition is focused on some common viewpoints, and these approaches do not perform well when there is a change in viewpoint. Human actions are performed in a 3-dimensional environment and are projected to a 2-dimensional space when captured as a video from a given viewpoint. Therefore, an action will have a different spatio-temporal appearance from different viewpoints. The research in view-invariant action recognition addresses this problem and focuses on recognizing human actions from unseen viewpoints. △ Less

Submitted 1 September, 2020; originally announced September 2020.