Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–14 of 14 results for author: Dhingra, N

Searching in archive cs. Search in all archives.
.
  1. arXiv:2604.12634  [pdf, ps, other

    cs.AI cs.CL cs.LG cs.MA

    RPRA: Predicting an LLM-Judge for Efficient but Performant Inference

    Authors: Dylan R. Ashley, Gaël Le Lan, Changsheng Zhao, Naina Dhingra, Zhipeng Cai, Ernie Chang, Mingchen Zhuge, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber

    Abstract: Large language models (LLMs) face a fundamental trade-off between computational efficiency (e.g., number of parameters) and output quality, especially when deployed on computationally limited devices such as phones or laptops. One way to address this challenge is by following the example of humans and have models ask for help when they believe they are incapable of solving a problem on their own;… ▽ More

    Submitted 14 April, 2026; originally announced April 2026.

    Comments: 10 pages in main text + 6 pages of references + 36 pages of appendices, 12 figures in main text + 37 figures in appendices, 2 tables in main text + 3 table in appendices, 13 prompts in appendices

    MSC Class: 68T07 ACM Class: I.2.6; I.2.7; I.2.11

  2. arXiv:2604.04874  [pdf, ps, other

    cs.CV

    Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction

    Authors: Ahan Shabanov, Peter Hedman, Ethan Weber, Zhengqin Li, Denis Rozumny, Gael Le Lan, Naina Dhingra, Lei Luo, Andrea Vedaldi, Christian Richardt, Andrea Tagliasacchi, Bo Zhu, Numair Khan

    Abstract: We present Free-Range Gaussians, a multi-view reconstruction method that predicts non-pixel, non-voxel-aligned 3D Gaussians from as few as four images. This is done through flow matching over Gaussian parameters. Our generative formulation of reconstruction allows the model to be supervised with non-grid-aligned 3D data, and enables it to synthesize plausible content in unobserved regions. Thus, i… ▽ More

    Submitted 6 April, 2026; originally announced April 2026.

    Comments: Project Page: https://free-range-gaussians.github.io

  3. arXiv:2601.14674  [pdf, ps, other

    cs.CV cs.LG

    LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models

    Authors: Mingyang Xie, Numair Khan, Tianfu Wang, Naina Dhingra, Seonghyeon Nam, Haitao Yang, Zhuo Hui, Christopher Metzler, Andrea Vedaldi, Hamed Pirsiavash, Lei Luo

    Abstract: Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory. Existing methods face two distinct challenges. Geometrically unconditioned models lack spatial awareness, leading to drift and deformation under viewpoint changes. On the other hand, geometrically-conditioned models depend on estimated depth and explicit reconstruction, making… ▽ More

    Submitted 2 April, 2026; v1 submitted 21 January, 2026; originally announced January 2026.

  4. arXiv:2507.06075  [pdf, ps, other

    cs.CV

    Discontinuity-aware Normal Integration for Generic Central Camera Models

    Authors: Francesco Milano, Manuel López-Antequera, Naina Dhingra, Roland Siegwart, Robert Thiel

    Abstract: Recovering a 3D surface from its surface normal map, a problem known as normal integration, is a key component for photometric shape reconstruction techniques such as shape-from-shading and photometric stereo. The vast majority of existing approaches for normal integration handle only implicitly the presence of depth discontinuities and are limited to orthographic or ideal pinhole cameras. In this… ▽ More

    Submitted 1 September, 2025; v1 submitted 8 July, 2025; originally announced July 2025.

    Comments: Accepted by the IEEE/CVF International Conference on Computer Vision (ICCV) 2025, as highlight. 19 pages, 13 figures, 9 tables

  5. arXiv:2305.07214  [pdf, other

    cs.CV cs.AI

    MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition

    Authors: Xinyu Gong, Sreyas Mohan, Naina Dhingra, Jean-Charles Bazin, Yilei Li, Zhangyang Wang, Rakesh Ranjan

    Abstract: In this paper, we study a novel problem in egocentric action recognition, which we term as "Multimodal Generalization" (MMG). MMG aims to study how systems can generalize when data from certain modalities is limited or even completely missing. We thoroughly investigate MMG in the context of standard supervised action recognition and the more challenging few-shot setting for learning new action cat… ▽ More

    Submitted 11 May, 2023; originally announced May 2023.

    Comments: Accepted to CVPR 2023

  6. HeadPosr: End-to-end Trainable Head Pose Estimation using Transformer Encoders

    Authors: Naina Dhingra

    Abstract: In this paper, HeadPosr is proposed to predict the head poses using a single RGB image. \textit{HeadPosr} uses a novel architecture which includes a transformer encoder. In concrete, it consists of: (1) backbone; (2) connector; (3) transformer encoder; (4) prediction head. The significance of using a transformer encoder for HPE is studied. An extensive ablation study is performed on varying the (1… ▽ More

    Submitted 7 February, 2022; originally announced February 2022.

    Comments: 8 pages, 4 figures

    Journal ref: In 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021) (pp. 1-8)

  7. arXiv:2202.03544  [pdf, other

    cs.CV

    LwPosr: Lightweight Efficient Fine-Grained Head Pose Estimation

    Authors: Naina Dhingra

    Abstract: This paper presents a lightweight network for head pose estimation (HPE) task. While previous approaches rely on convolutional neural networks, the proposed network \textit{LwPosr} uses mixture of depthwise separable convolutional (DSC) and transformer encoder layers which are structured in two streams and three stages to provide fine-grained regression for predicting head poses. The quantitative… ▽ More

    Submitted 7 February, 2022; originally announced February 2022.

    Comments: 11 pages, 3 figures

    Journal ref: In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 1495-1505), 2022

  8. arXiv:2109.05353  [pdf, other

    cs.CV cs.AI

    Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network

    Authors: Naina Dhingra, George Chogovadze, Andreas Kunz

    Abstract: We present Border-SegGCN, a novel architecture to improve semantic segmentation by refining the border outline using graph convolutional networks (GCN). The semantic segmentation network such as Unet or DeepLabV3+ is used as a base network to have pre-segmented output. This output is converted into a graphical structure and fed into the GCN to improve the border pixel prediction of the pre-segment… ▽ More

    Submitted 11 September, 2021; originally announced September 2021.

    Comments: 8 pages

  9. arXiv:2109.05346  [pdf, other

    cs.CV cs.AI

    BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation

    Authors: Naina Dhingra, Florian Ritter, Andreas Kunz

    Abstract: Scene graphs are nodes and edges consisting of objects and object-object relationships, respectively. Scene graph generation (SGG) aims to identify the objects and their relationships. We propose a bidirectional GRU (BiGRU) transformer network (BGT-Net) for the scene graph generation for images. This model implements novel object-object communication to enhance the object information using a BiGRU… ▽ More

    Submitted 11 September, 2021; originally announced September 2021.

    Comments: 8 pages, 7 supplementary pages

    Journal ref: Journal-ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition pages: 2150--2159 year: 2021

  10. arXiv:2001.03687  [pdf, other

    cs.HC cs.RO eess.SP

    Recognition and Localisation of Pointing Gestures using a RGB-D Camera

    Authors: Naina Dhingra, Eugenio Valli, Andreas Kunz

    Abstract: Non-verbal communication is part of our regular conversation, and multiple gestures are used to exchange information. Among those gestures, pointing is the most important one. If such gestures cannot be perceived by other team members, e.g. by blind and visually impaired people (BVIP), they lack important information and can hardly participate in a lively workflow. Thus, this paper describes a sys… ▽ More

    Submitted 10 January, 2020; originally announced January 2020.

    Comments: 8 pages, 5 figures

  11. arXiv:2001.01083  [pdf, other

    cs.CV cs.LG eess.IV eess.SP

    Res3ATN -- Deep 3D Residual Attention Network for Hand Gesture Recognition in Videos

    Authors: Naina Dhingra, Andreas Kunz

    Abstract: Hand gesture recognition is a strenuous task to solve in videos. In this paper, we use a 3D residual attention network which is trained end to end for hand gesture recognition. Based on the stacked multiple attention blocks, we build a 3D network which generates different features at each attention block. Our 3D attention based residual network (Res3ATN) can be built and extended to very deep laye… ▽ More

    Submitted 4 January, 2020; originally announced January 2020.

    Comments: 10 pages, 4 figures, International Conference on 3D Vision (3DV 2019), Quebec City, Canada, September 16-19, 2019

    Journal ref: 2019 International Conference on 3D Vision (3DV), 491--501, 2019

  12. arXiv:1807.01739  [pdf, other

    math.OC cs.AI cs.LG eess.SY

    Proximal algorithms for large-scale statistical modeling and sensor/actuator selection

    Authors: Armin Zare, Hesameddin Mohammadi, Neil K. Dhingra, Tryphon T. Georgiou, Mihailo R. Jovanović

    Abstract: Several problems in modeling and control of stochastically-driven dynamical systems can be cast as regularized semi-definite programs. We examine two such representative problems and show that they can be formulated in a similar manner. The first, in statistical modeling, seeks to reconcile observed statistics by suitably and minimally perturbing prior dynamics. The second seeks to optimally selec… ▽ More

    Submitted 26 December, 2019; v1 submitted 4 July, 2018; originally announced July 2018.

    Comments: To appear in IEEE Trans. Automat. Control

  13. arXiv:1712.10128  [pdf, other

    math.OC cs.DC eess.SY

    Structured decentralized control of positive systems with applications to combination drug therapy and leader selection in directed networks

    Authors: Neil K. Dhingra, Marcello Colombino, Mihailo R. Jovanović

    Abstract: We study a class of structured optimal control problems in which the main diagonal of the dynamic matrix is a linear function of the design variable. While such problems are in general challenging and nonconvex, for positive systems we prove convexity of the $H_2$ and $H_\infty$ optimal control formulations which allow for arbitrary convex constraints and regularization of the control input. Moreo… ▽ More

    Submitted 4 March, 2018; v1 submitted 29 December, 2017; originally announced December 2017.

    Comments: 11 pages, 7 figures

    Journal ref: IEEE Trans. Control Netw. Syst., vol. 6, no. 1, pp. 352-362, March 2019

  14. arXiv:1709.01610  [pdf, other

    math.OC cs.AI eess.SY nlin.AO

    A second order primal-dual method for nonsmooth convex composite optimization

    Authors: Neil K. Dhingra, Sei Zhen Khong, Mihailo R. Jovanović

    Abstract: We develop a second order primal-dual method for optimization problems in which the objective function is given by the sum of a strongly convex twice differentiable term and a possibly nondifferentiable convex regularizer. After introducing an auxiliary variable, we utilize the proximal operator of the nonsmooth regularizer to transform the associated augmented Lagrangian into a function that is o… ▽ More

    Submitted 27 August, 2020; v1 submitted 5 September, 2017; originally announced September 2017.

    Comments: 32 pages, 8 figures