Showing 1–39 of 39 results for author: Artemov, A

Towards Space-Based Environmentally-Adaptive Grasping

Authors: Leonidas Askianakis, Aleksandr Artemov

Abstract: Robotic manipulation in unstructured environments requires reliable execution under diverse conditions, yet many state-of-the-art systems still struggle with high-dimensional action spaces, sparse rewards, and slow generalization beyond carefully curated training scenarios. We study these limitations through the example of grasping in space environments. We learn control policies directly in a lea… ▽ More Robotic manipulation in unstructured environments requires reliable execution under diverse conditions, yet many state-of-the-art systems still struggle with high-dimensional action spaces, sparse rewards, and slow generalization beyond carefully curated training scenarios. We study these limitations through the example of grasping in space environments. We learn control policies directly in a learned latent manifold that fuses (grammarizes) multiple modalities into a structured representation for policy decision-making. Building on GPU-accelerated physics simulation, we instantiate a set of single-shot manipulation tasks and achieve over 95% task success with Soft Actor-Critic (SAC)-based reinforcement learning in less than 1M environment steps, under continuously varying grasping conditions from step 1. This empirically shows faster convergence than representative state-of-the-art visual baselines under the same open-loop single-shot conditions. Our analysis indicates that explicitly reasoning in latent space yields more sample-efficient learning and improved robustness to novel object and gripper geometries, environmental clutter, and sensor configurations compared to standard baselines. We identify remaining limitations and outline directions toward fully adaptive and generalizable grasping in the extreme conditions of space. △ Less

Submitted 29 January, 2026; originally announced January 2026.

Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks

Authors: Dmitrii Pozdeev, Alexey Artemov, Ananta R. Bhattarai, Artem Sevastopolsky

Abstract: We propose DenseMarks - a new learned representation for human heads, enabling high-quality dense correspondences of human head images. For a 2D image of a human head, a Vision Transformer network predicts a 3D embedding for each pixel, which corresponds to a location in a 3D canonical unit cube. In order to train our network, we collect a dataset of pairwise point matches, estimated by a state-of… ▽ More We propose DenseMarks - a new learned representation for human heads, enabling high-quality dense correspondences of human head images. For a 2D image of a human head, a Vision Transformer network predicts a 3D embedding for each pixel, which corresponds to a location in a 3D canonical unit cube. In order to train our network, we collect a dataset of pairwise point matches, estimated by a state-of-the-art point tracker over a collection of diverse in-the-wild talking heads videos, and guide the mapping via a contrastive loss, encouraging matched points to have close embeddings. We further employ multi-task learning with face landmarks and segmentation constraints, as well as imposing spatial continuity of embeddings through latent cube features, which results in an interpretable and queryable canonical space. The representation can be used for finding common semantic parts, face/head tracking, and stereo reconstruction. Due to the strong supervision, our method is robust to pose variations and covers the entire head, including hair. Additionally, the canonical space bottleneck makes sure the obtained representations are consistent across diverse poses and individuals. We demonstrate state-of-the-art results in geometry-aware point matching and monocular head tracking with 3D Morphable Models. The code and the model checkpoint will be made available to the public. △ Less

Submitted 4 November, 2025; originally announced November 2025.

Comments: Project page: https://diddone.github.io/densemarks/ .Video: https://youtu.be/o8DOOYFW0gI .21 pages, 13 figures, 2 tables

A3D: Does Diffusion Dream about 3D Alignment?

Authors: Savva Ignatyev, Nina Konovalova, Daniil Selikhanovych, Oleg Voynov, Nikolay Patakin, Ilya Olkov, Dmitry Senushkin, Alexey Artemov, Anton Konushin, Alexander Filippov, Peter Wonka, Evgeny Burnaev

Abstract: We tackle the problem of text-driven 3D generation from a geometry alignment perspective. Given a set of text prompts, we aim to generate a collection of objects with semantically corresponding parts aligned across them. Recent methods based on Score Distillation have succeeded in distilling the knowledge from 2D diffusion models to high-quality representations of the 3D objects. These methods han… ▽ More We tackle the problem of text-driven 3D generation from a geometry alignment perspective. Given a set of text prompts, we aim to generate a collection of objects with semantically corresponding parts aligned across them. Recent methods based on Score Distillation have succeeded in distilling the knowledge from 2D diffusion models to high-quality representations of the 3D objects. These methods handle multiple text queries separately, and therefore the resulting objects have a high variability in object pose and structure. However, in some applications, such as 3D asset design, it may be desirable to obtain a set of objects aligned with each other. In order to achieve the alignment of the corresponding parts of the generated objects, we propose to embed these objects into a common latent space and optimize the continuous transitions between these objects. We enforce two kinds of properties of these transitions: smoothness of the transition and plausibility of the intermediate objects along the transition. We demonstrate that both of these properties are essential for good alignment. We provide several practical scenarios that benefit from alignment between the objects, including 3D editing and object hybridization, and experimentally demonstrate the effectiveness of our method. https://voyleg.github.io/a3d/ △ Less

Submitted 16 March, 2025; v1 submitted 21 June, 2024; originally announced June 2024.

DeepMIF: Deep Monotonic Implicit Fields for Large-Scale LiDAR 3D Mapping

Authors: Kutay Yılmaz, Matthias Nießner, Anastasiia Kornilova, Alexey Artemov

Abstract: Recently, significant progress has been achieved in sensing real large-scale outdoor 3D environments, particularly by using modern acquisition equipment such as LiDAR sensors. Unfortunately, they are fundamentally limited in their ability to produce dense, complete 3D scenes. To address this issue, recent learning-based methods integrate neural implicit representations and optimizable feature grid… ▽ More Recently, significant progress has been achieved in sensing real large-scale outdoor 3D environments, particularly by using modern acquisition equipment such as LiDAR sensors. Unfortunately, they are fundamentally limited in their ability to produce dense, complete 3D scenes. To address this issue, recent learning-based methods integrate neural implicit representations and optimizable feature grids to approximate surfaces of 3D scenes. However, naively fitting samples along raw LiDAR rays leads to noisy 3D mapping results due to the nature of sparse, conflicting LiDAR measurements. Instead, in this work we depart from fitting LiDAR data exactly, instead letting the network optimize a non-metric monotonic implicit field defined in 3D space. To fit our field, we design a learning system integrating a monotonicity loss that enables optimizing neural monotonic fields and leverages recent progress in large-scale 3D mapping. Our algorithm achieves high-quality dense 3D mapping performance as captured by multiple quantitative and perceptual measures and visual results obtained for Mai City, Newer College, and KITTI benchmarks. The code of our approach will be made publicly available. △ Less

Submitted 28 August, 2024; v1 submitted 26 March, 2024; originally announced March 2024.

Comments: 8 pages, 6 figures

AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans

Authors: Cedric Perauer, Laurenz Adrian Heidrich, Haifan Zhang, Matthias Nießner, Anastasiia Kornilova, Alexey Artemov

Abstract: Recently, progress in acquisition equipment such as LiDAR sensors has enabled sensing increasingly spacious outdoor 3D environments. Making sense of such 3D acquisitions requires fine-grained scene understanding, such as constructing instance-based 3D scene segmentations. Commonly, a neural network is trained for this task; however, this requires access to a large, densely annotated dataset, which… ▽ More Recently, progress in acquisition equipment such as LiDAR sensors has enabled sensing increasingly spacious outdoor 3D environments. Making sense of such 3D acquisitions requires fine-grained scene understanding, such as constructing instance-based 3D scene segmentations. Commonly, a neural network is trained for this task; however, this requires access to a large, densely annotated dataset, which is widely known to be challenging to obtain. To address this issue, in this work we propose to predict instance segmentations for 3D scenes in an unsupervised way, without relying on ground-truth annotations. To this end, we construct a learning framework consisting of two components: (1) a pseudo-annotation scheme for generating initial unsupervised pseudo-labels; and (2) a self-training algorithm for instance segmentation to fit robust, accurate instances from initial noisy proposals. To enable generating 3D instance mask proposals, we construct a weighted proxy-graph by connecting 3D points with edges integrating multi-modal image- and point-based self-supervised features, and perform graph-cuts to isolate individual pseudo-instances. We then build on a state-of-the-art point-based architecture and train a 3D instance segmentation model, resulting in significant refinement of initial proposals. To scale to arbitrary complexity 3D scenes, we design our algorithm to operate on local 3D point chunks and construct a merging step to generate scene-level instance segmentations. Experiments on the challenging SemanticKITTI benchmark demonstrate the potential of our approach, where it attains 13.3% higher Average Precision and 9.1% higher F1 score compared to the best-performing baseline. The code will be made publicly available at https://github.com/artonson/autoinst. △ Less

Submitted 28 August, 2024; v1 submitted 24 March, 2024; originally announced March 2024.

Comments: 8 pages, 7 figures, to be published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024

ACM Class: I.4.6; I.2.9

PRS: Sharp Feature Priors for Resolution-Free Surface Remeshing

Authors: Natalia Soboleva, Olga Gorbunova, Maria Ivanova, Evgeny Burnaev, Matthias Nießner, Denis Zorin, Alexey Artemov

Abstract: Surface reconstruction with preservation of geometric features is a challenging computer vision task. Despite significant progress in implicit shape reconstruction, state-of-the-art mesh extraction methods often produce aliased, perceptually distorted surfaces and lack scalability to high-resolution 3D shapes. We present a data-driven approach for automatic feature detection and remeshing that req… ▽ More Surface reconstruction with preservation of geometric features is a challenging computer vision task. Despite significant progress in implicit shape reconstruction, state-of-the-art mesh extraction methods often produce aliased, perceptually distorted surfaces and lack scalability to high-resolution 3D shapes. We present a data-driven approach for automatic feature detection and remeshing that requires only a coarse, aliased mesh as input and scales to arbitrary resolution reconstructions. We define and learn a collection of surface-based fields to (1) capture sharp geometric features in the shape with an implicit vertexwise model and (2) approximate improvements in normals alignment obtained by applying edge-flips with an edgewise model. To support scaling to arbitrary complexity shapes, we learn our fields using local triangulated patches, fusing estimates on complete surface meshes. Our feature remeshing algorithm integrates the learned fields as sharp feature priors and optimizes vertex placement and mesh connectivity for maximum expected surface improvement. On a challenging collection of high-resolution shape reconstructions in the ABC dataset, our algorithm improves over state-of-the-art by 26% normals F-score and 42% perceptual $\text{RMSE}_{\text{v}}$. △ Less

Submitted 30 November, 2023; originally announced November 2023.

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

Authors: Yawar Siddiqui, Antonio Alliegro, Alexey Artemov, Tatiana Tommasi, Daniele Sirigatti, Vladislav Rosov, Angela Dai, Matthias Nießner

Abstract: We introduce MeshGPT, a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes, in contrast to dense triangle meshes extracted by iso-surfacing methods from neural fields. Inspired by recent advances in powerful large language models, we adopt a sequence-based approach to autoregressively generate triangle meshes as sequences of triangles. We fir… ▽ More We introduce MeshGPT, a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes, in contrast to dense triangle meshes extracted by iso-surfacing methods from neural fields. Inspired by recent advances in powerful large language models, we adopt a sequence-based approach to autoregressively generate triangle meshes as sequences of triangles. We first learn a vocabulary of latent quantized embeddings, using graph convolutions, which inform these embeddings of the local mesh geometry and topology. These embeddings are sequenced and decoded into triangles by a decoder, ensuring that they can effectively reconstruct the mesh. A transformer is then trained on this learned vocabulary to predict the index of the next embedding given previous embeddings. Once trained, our model can be autoregressively sampled to generate new triangle meshes, directly generating compact meshes with sharp edges, more closely imitating the efficient triangulation patterns of human-crafted meshes. MeshGPT demonstrates a notable improvement over state of the art mesh generation methods, with a 9% increase in shape coverage and a 30-point enhancement in FID scores across various categories. △ Less

Submitted 26 November, 2023; originally announced November 2023.

Comments: Project Page: https://nihalsid.github.io/mesh-gpt/, Video: https://youtu.be/UV90O1_69_o

SSR-2D: Semantic 3D Scene Reconstruction from 2D Images

Authors: Junwen Huang, Alexey Artemov, Yujin Chen, Shuaifeng Zhi, Kai Xu, Matthias Nießner

Abstract: Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations. The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding s… ▽ More Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations. The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding source RGB-D images, fusing cross-domain features into volumetric embeddings to predict complete 3D geometry, color, and semantics with only 2D labeling which can be either manual or machine-generated. Our key technical innovation is to leverage differentiable rendering of color and semantics to bridge 2D observations and unknown 3D space, using the observed RGB images and 2D semantics as supervision, respectively. We additionally develop a learning pipeline and corresponding method to enable learning from imperfect predicted 2D labels, which could be additionally acquired by synthesizing in an augmented set of virtual training views complementing the original real captures, enabling more efficient self-supervision loop for semantics. As a result, our end-to-end trainable solution jointly addresses geometry completion, colorization, and semantic mapping from limited RGB-D images, without relying on any 3D ground-truth information. Our method achieves the state-of-the-art performance of semantic scene completion on two large-scale benchmark datasets MatterPort3D and ScanNet, surpasses baselines even with costly 3D annotations in predicting both geometry and semantics. To our knowledge, our method is also the first 2D-driven method addressing completion and semantic segmentation of real-world 3D scans simultaneously. △ Less

Submitted 5 June, 2024; v1 submitted 7 February, 2023; originally announced February 2023.

Scan2Part: Fine-grained and Hierarchical Part-level Understanding of Real-World 3D Scans

Authors: Alexandr Notchenko, Vladislav Ishimtsev, Alexey Artemov, Vadim Selyutin, Emil Bogomolov, Evgeny Burnaev

Abstract: We propose Scan2Part, a method to segment individual parts of objects in real-world, noisy indoor RGB-D scans. To this end, we vary the part hierarchies of objects in indoor scenes and explore their effect on scene understanding models. Specifically, we use a sparse U-Net-based architecture that captures the fine-scale detail of the underlying 3D scan geometry by leveraging a multi-scale feature h… ▽ More We propose Scan2Part, a method to segment individual parts of objects in real-world, noisy indoor RGB-D scans. To this end, we vary the part hierarchies of objects in indoor scenes and explore their effect on scene understanding models. Specifically, we use a sparse U-Net-based architecture that captures the fine-scale detail of the underlying 3D scan geometry by leveraging a multi-scale feature hierarchy. In order to train our method, we introduce the Scan2Part dataset, which is the first large-scale collection providing detailed semantic labels at the part level in the real-world setting. In total, we provide 242,081 correspondences between 53,618 PartNet parts of 2,477 ShapeNet objects and 1,506 ScanNet scenes, at two spatial resolutions of 2 cm$^3$ and 5 cm$^3$. As output, we are able to predict fine-grained per-object part labels, even when the geometry is coarse or partially missing. △ Less

Submitted 6 June, 2022; originally announced June 2022.

Comments: In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

Multi-sensor large-scale dataset for multi-view 3D reconstruction

Authors: Oleg Voynov, Gleb Bobrovskikh, Pavel Karpyshev, Saveliy Galochkin, Andrei-Timotei Ardelean, Arseniy Bozhenko, Ekaterina Karmanova, Pavel Kopanev, Yaroslav Labutin-Rymsho, Ruslan Rakhimov, Aleksandr Safin, Valerii Serpiva, Alexey Artemov, Evgeny Burnaev, Dzmitry Tsetserukou, Denis Zorin

Abstract: We present a new multi-sensor dataset for multi-view 3D surface reconstruction. It includes registered RGB and depth data from sensors of different resolutions and modalities: smartphones, Intel RealSense, Microsoft Kinect, industrial cameras, and structured-light scanner. The scenes are selected to emphasize a diverse set of material properties challenging for existing algorithms. We provide arou… ▽ More We present a new multi-sensor dataset for multi-view 3D surface reconstruction. It includes registered RGB and depth data from sensors of different resolutions and modalities: smartphones, Intel RealSense, Microsoft Kinect, industrial cameras, and structured-light scanner. The scenes are selected to emphasize a diverse set of material properties challenging for existing algorithms. We provide around 1.4 million images of 107 different scenes acquired from 100 viewing directions under 14 lighting conditions. We expect our dataset will be useful for evaluation and training of 3D reconstruction algorithms and for related tasks. The dataset is available at skoltech3d.appliedai.tech. △ Less

Submitted 28 March, 2023; v1 submitted 11 March, 2022; originally announced March 2022.

Comments: v4: final camera-ready version

Can We Use Neural Regularization to Solve Depth Super-Resolution?

Authors: Milena Gazdieva, Oleg Voynov, Alexey Artemov, Youyi Zheng, Luiz Velho, Evgeny Burnaev

Abstract: Depth maps captured with commodity sensors often require super-resolution to be used in applications. In this work we study a super-resolution approach based on a variational problem statement with Tikhonov regularization where the regularizer is parametrized with a deep neural network. This approach was previously applied successfully in photoacoustic tomography. We experimentally show that its a… ▽ More Depth maps captured with commodity sensors often require super-resolution to be used in applications. In this work we study a super-resolution approach based on a variational problem statement with Tikhonov regularization where the regularizer is parametrized with a deep neural network. This approach was previously applied successfully in photoacoustic tomography. We experimentally show that its application to depth map super-resolution is difficult, and provide suggestions about the reasons for that. △ Less

Submitted 21 December, 2021; originally announced December 2021.

Comments: 9 pages

3D Parametric Wireframe Extraction Based on Distance Fields

Authors: Albert Matveev, Alexey Artemov, Denis Zorin, Evgeny Burnaev

Abstract: We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, constructs curve segmentation, and builds a topological graph fitted to the wireframe. As an output, we produce parametric spline curves that can be edite… ▽ More We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, constructs curve segmentation, and builds a topological graph fitted to the wireframe. As an output, we produce parametric spline curves that can be edited and sampled arbitrarily. We evaluate our method on 50 complex 3D shapes and compare it to the novel deep learning-based technique, demonstrating superior quality. △ Less

Submitted 20 April, 2022; v1 submitted 13 July, 2021; originally announced July 2021.

Unpaired Depth Super-Resolution in the Wild

Authors: Aleksandr Safin, Maxim Kan, Nikita Drobyshev, Oleg Voynov, Alexey Artemov, Alexander Filippov, Denis Zorin, Evgeny Burnaev

Abstract: Depth maps captured with commodity sensors are often of low quality and resolution; these maps need to be enhanced to be used in many applications. State-of-the-art data-driven methods of depth map super-resolution rely on registered pairs of low- and high-resolution depth maps of the same scenes. Acquisition of real-world paired data requires specialized setups. Another alternative, generating lo… ▽ More Depth maps captured with commodity sensors are often of low quality and resolution; these maps need to be enhanced to be used in many applications. State-of-the-art data-driven methods of depth map super-resolution rely on registered pairs of low- and high-resolution depth maps of the same scenes. Acquisition of real-world paired data requires specialized setups. Another alternative, generating low-resolution maps from high-resolution maps by subsampling, adding noise and other artificial degradation methods, does not fully capture the characteristics of real-world low-resolution images. As a consequence, supervised learning methods trained on such artificial paired data may not perform well on real-world low-resolution inputs. We consider an approach to depth super-resolution based on learning from unpaired data. While many techniques for unpaired image-to-image translation have been proposed, most fail to deliver effective hole-filling or reconstruct accurate surfaces using depth maps. We propose an unpaired learning method for depth super-resolution, which is based on a learnable degradation model, enhancement component and surface normal estimates as features to produce more accurate depth maps. We propose a benchmark for unpaired depth SR and demonstrate that our method outperforms existing unpaired methods and performs on par with paired. △ Less

Submitted 23 September, 2022; v1 submitted 25 May, 2021; originally announced May 2021.

Analysis of Basic Emotions in Texts Based on BERT Vector Representation

Authors: A. Artemov, A. Veselovskiy, I. Khasenevich, I. Bolokhov

Abstract: In the following paper the authors present a GAN-type model and the most important stages of its development for the task of emotion recognition in text. In particular, we propose an approach for generating a synthetic dataset of all possible emotions combinations based on manually labelled incomplete data. In the following paper the authors present a GAN-type model and the most important stages of its development for the task of emotion recognition in text. In particular, we propose an approach for generating a synthetic dataset of all possible emotions combinations based on manually labelled incomplete data. △ Less

Submitted 31 January, 2021; v1 submitted 21 January, 2021; originally announced January 2021.

Comments: 8 pages, 2 figures, 5 tables

ACM Class: I.2.6; I.2.7

Towards Part-Based Understanding of RGB-D Scans

Authors: Alexey Bokhovkin, Vladislav Ishimtsev, Emil Bogomolov, Denis Zorin, Alexey Artemov, Evgeny Burnaev, Angela Dai

Abstract: Recent advances in 3D semantic scene understanding have shown impressive progress in 3D instance segmentation, enabling object-level reasoning about 3D scenes; however, a finer-grained understanding is required to enable interactions with objects and their functional understanding. Thus, we propose the task of part-based scene understanding of real-world 3D environments: from an RGB-D scan of a sc… ▽ More Recent advances in 3D semantic scene understanding have shown impressive progress in 3D instance segmentation, enabling object-level reasoning about 3D scenes; however, a finer-grained understanding is required to enable interactions with objects and their functional understanding. Thus, we propose the task of part-based scene understanding of real-world 3D environments: from an RGB-D scan of a scene, we detect objects, and for each object predict its decomposition into geometric part masks, which composed together form the complete geometry of the observed object. We leverage an intermediary part graph representation to enable robust completion as well as building of part priors, which we use to construct the final part mask predictions. Our experiments demonstrate that guiding part understanding through part graph to part prior-based predictions significantly outperforms alternative approaches to the task of semantic part completion. △ Less

Submitted 3 December, 2020; originally announced December 2020.

Comments: https://youtu.be/iuixmPNs4v4

DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes

Authors: Albert Matveev, Ruslan Rakhimov, Alexey Artemov, Gleb Bobrovskikh, Vage Egiazarian, Emil Bogomolov, Daniele Panozzo, Denis Zorin, Evgeny Burnaev

Abstract: We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes. Differently from existing data-driven methods, which reduce this problem to feature classification, we propose to regress a scalar field representing the distance from point samples to the closest feature line on local patches. Our approach is the first that scale… ▽ More We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes. Differently from existing data-driven methods, which reduce this problem to feature classification, we propose to regress a scalar field representing the distance from point samples to the closest feature line on local patches. Our approach is the first that scales to massive point clouds by fusing distance-to-feature estimates obtained on individual patches. We extensively evaluate our approach against related state-of-the-art methods on newly proposed synthetic and real-world 3D CAD model benchmarks. Our approach not only outperforms these (with improvements in Recall and False Positives Rates), but generalizes to real-world scans after training our model on synthetic data and fine-tuning it on a small dataset of scanned data. We demonstrate a downstream application, where we reconstruct an explicit representation of straight and curved sharp feature lines from range scan data. △ Less

Submitted 26 May, 2022; v1 submitted 30 November, 2020; originally announced November 2020.

The Chunks and Tasks Matrix Library 2.0

Authors: Emanuel H. Rubensson, Elias Rudberg, Anastasia Kruchinina, Anton G. Artemov

Abstract: We present a C++ header-only parallel sparse matrix library, based on sparse quadtree representation of matrices using the Chunks and Tasks programming model. The library implements a number of sparse matrix algorithms for distributed memory parallelization that are able to dynamically exploit data locality to avoid movement of data. This is demonstrated for the example of block-sparse matrix-matr… ▽ More We present a C++ header-only parallel sparse matrix library, based on sparse quadtree representation of matrices using the Chunks and Tasks programming model. The library implements a number of sparse matrix algorithms for distributed memory parallelization that are able to dynamically exploit data locality to avoid movement of data. This is demonstrated for the example of block-sparse matrix-matrix multiplication applied to three sequences of matrices with different nonzero structure, using the CHT-MPI 2.0 runtime library implementation of the Chunks and Tasks model. The runtime library succeeds to dynamically load balance the calculation regardless of the sparsity structure. △ Less

Submitted 23 November, 2020; originally announced November 2020.

MSC Class: 65F50 ACM Class: D.1.3; G.1.3; G.4

CAD-Deform: Deformable Fitting of CAD Models to 3D Scans

Authors: Vladislav Ishimtsev, Alexey Bokhovkin, Alexey Artemov, Savva Ignatyev, Matthias Niessner, Denis Zorin, Evgeny Burnaev

Abstract: Shape retrieval and alignment are a promising avenue towards turning 3D scans into lightweight CAD representations that can be used for content creation such as mobile or AR/VR gaming scenarios. Unfortunately, CAD model retrieval is limited by the availability of models in standard 3D shape collections (e.g., ShapeNet). In this work, we address this shortcoming by introducing CAD-Deform, a method… ▽ More Shape retrieval and alignment are a promising avenue towards turning 3D scans into lightweight CAD representations that can be used for content creation such as mobile or AR/VR gaming scenarios. Unfortunately, CAD model retrieval is limited by the availability of models in standard 3D shape collections (e.g., ShapeNet). In this work, we address this shortcoming by introducing CAD-Deform, a method which obtains more accurate CAD-to-scan fits by non-rigidly deforming retrieved CAD models. Our key contribution is a new non-rigid deformation model incorporating smooth transformations and preservation of sharp features, that simultaneously achieves very tight fits from CAD models to the 3D scan and maintains the clean, high-quality surface properties of hand-modeled CAD objects. A series of thorough experiments demonstrate that our method achieves significantly tighter scan-to-CAD fits, allowing a more accurate digital replica of the scanned real-world environment while preserving important geometric features present in synthetic CAD environments. △ Less

Submitted 23 July, 2020; originally announced July 2020.

Comments: 25 pages, 13 figures, ECCV 2020

Geometric Attention for Prediction of Differential Properties in 3D Point Clouds

Authors: Albert Matveev, Alexey Artemov, Denis Zorin, Evgeny Burnaev

Abstract: Estimation of differential geometric quantities in discrete 3D data representations is one of the crucial steps in the geometry processing pipeline. Specifically, estimating normals and sharp feature lines from raw point cloud helps improve meshing quality and allows us to use more precise surface reconstruction techniques. When designing a learnable approach to such problems, the main difficulty… ▽ More Estimation of differential geometric quantities in discrete 3D data representations is one of the crucial steps in the geometry processing pipeline. Specifically, estimating normals and sharp feature lines from raw point cloud helps improve meshing quality and allows us to use more precise surface reconstruction techniques. When designing a learnable approach to such problems, the main difficulty is selecting neighborhoods in a point cloud and incorporating geometric relations between the points. In this study, we present a geometric attention mechanism that can provide such properties in a learnable fashion. We establish the usefulness of the proposed technique with several experiments on the prediction of normal vectors and the extraction of feature lines. △ Less

Submitted 6 August, 2020; v1 submitted 6 July, 2020; originally announced July 2020.

Making DensePose fast and light

Authors: Ruslan Rakhimov, Emil Bogomolov, Alexandr Notchenko, Fung Mao, Alexey Artemov, Denis Zorin, Evgeny Burnaev

Abstract: DensePose estimation task is a significant step forward for enhancing user experience computer vision applications ranging from augmented reality to cloth fitting. Existing neural network models capable of solving this task are heavily parameterized and a long way from being transferred to an embedded or mobile device. To enable Dense Pose inference on the end device with current models, one needs… ▽ More DensePose estimation task is a significant step forward for enhancing user experience computer vision applications ranging from augmented reality to cloth fitting. Existing neural network models capable of solving this task are heavily parameterized and a long way from being transferred to an embedded or mobile device. To enable Dense Pose inference on the end device with current models, one needs to support an expensive server-side infrastructure and have a stable internet connection. To make things worse, mobile and embedded devices do not always have a powerful GPU inside. In this work, we target the problem of redesigning the DensePose R-CNN model's architecture so that the final network retains most of its accuracy but becomes more light-weight and fast. To achieve that, we tested and incorporated many deep learning innovations from recent years, specifically performing an ablation study on 23 efficient backbone architectures, multiple two-stage detection pipeline modifications, and custom model quantization methods. As a result, we achieved $17\times$ model size reduction and $2\times$ latency improvement compared to the baseline model. △ Less

Submitted 9 July, 2020; v1 submitted 26 June, 2020; originally announced June 2020.

Latent Video Transformer

Authors: Ruslan Rakhimov, Denis Volkhonskiy, Alexey Artemov, Denis Zorin, Evgeny Burnaev

Abstract: The video generation task can be formulated as a prediction of future video frames given some past frames. Recent generative models for videos face the problem of high computational requirements. Some models require up to 512 Tensor Processing Units for parallel training. In this work, we address this problem via modeling the dynamics in a latent space. After the transformation of frames into the… ▽ More The video generation task can be formulated as a prediction of future video frames given some past frames. Recent generative models for videos face the problem of high computational requirements. Some models require up to 512 Tensor Processing Units for parallel training. In this work, we address this problem via modeling the dynamics in a latent space. After the transformation of frames into the latent space, our model predicts latent representation for the next frames in an autoregressive manner. We demonstrate the performance of our approach on BAIR Robot Pushing and Kinetics-600 datasets. The approach tends to reduce requirements to 8 Graphical Processing Units for training the models while maintaining comparable generation quality. △ Less

Submitted 18 June, 2020; originally announced June 2020.

Data-driven models and computational tools for neurolinguistics: a language technology perspective

Authors: Ekaterina Artemova, Amir Bakarov, Aleksey Artemov, Evgeny Burnaev, Maxim Sharaev

Abstract: In this paper, our focus is the connection and influence of language technologies on the research in neurolinguistics. We present a review of brain imaging-based neurolinguistic studies with a focus on the natural language representations, such as word embeddings and pre-trained language models. Mutual enrichment of neurolinguistics and language technologies leads to development of brain-aware nat… ▽ More In this paper, our focus is the connection and influence of language technologies on the research in neurolinguistics. We present a review of brain imaging-based neurolinguistic studies with a focus on the natural language representations, such as word embeddings and pre-trained language models. Mutual enrichment of neurolinguistics and language technologies leads to development of brain-aware natural language representations. The importance of this research area is emphasized by medical applications. △ Less

Submitted 23 March, 2020; originally announced March 2020.

Comments: 37 pages, 1 figure

Journal ref: Journal of Cognitive Science, 2020

Deep Vectorization of Technical Drawings

Authors: Vage Egiazarian, Oleg Voynov, Alexey Artemov, Denis Volkhonskiy, Aleksandr Safin, Maria Taktasheva, Denis Zorin, Evgeny Burnaev

Abstract: We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images. Our method includes (1) a deep learning-based cleaning stage to eliminate the background and imperfections in the image and fill in missing parts, (2) a transformer-based network to estimate vector primitives, and (3) optimization procedure to obtain the final primi… ▽ More We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images. Our method includes (1) a deep learning-based cleaning stage to eliminate the background and imperfections in the image and fill in missing parts, (2) a transformer-based network to estimate vector primitives, and (3) optimization procedure to obtain the final primitive configurations. We train the networks on synthetic data, renderings of vector line drawings, and manually vectorized scans of line drawings. Our method quantitatively and qualitatively outperforms a number of existing techniques on a collection of representative technical drawings. △ Less

Submitted 30 July, 2020; v1 submitted 11 March, 2020; originally announced March 2020.

Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D Point Clouds

Authors: Vage Egiazarian, Savva Ignatyev, Alexey Artemov, Oleg Voynov, Andrey Kravchenko, Youyi Zheng, Luiz Velho, Evgeny Burnaev

Abstract: Constructing high-quality generative models for 3D shapes is a fundamental task in computer vision with diverse applications in geometry processing, engineering, and design. Despite the recent progress in deep generative modelling, synthesis of finely detailed 3D surfaces, such as high-resolution point clouds, from scratch has not been achieved with existing approaches. In this work, we propose to… ▽ More Constructing high-quality generative models for 3D shapes is a fundamental task in computer vision with diverse applications in geometry processing, engineering, and design. Despite the recent progress in deep generative modelling, synthesis of finely detailed 3D surfaces, such as high-resolution point clouds, from scratch has not been achieved with existing approaches. In this work, we propose to employ the latent-space Laplacian pyramid representation within a hierarchical generative model for 3D point clouds. We combine the recently proposed latent-space GAN and Laplacian GAN architectures to form a multi-scale model capable of generating 3D point clouds at increasing levels of detail. Our evaluation demonstrates that our model outperforms the existing generative models for 3D point clouds. △ Less

Submitted 13 December, 2019; originally announced December 2019.

Weakly Supervised Fine Tuning Approach for Brain Tumor Segmentation Problem

Authors: Sergey Pavlov, Alexey Artemov, Maksim Sharaev, Alexander Bernstein, Evgeny Burnaev

Abstract: Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain. In contrast, image-level annotations, where only the presence of lesion is marked, are generally cheap, generated in far larger volumes compared to pixel-level labels, and contain less labeling noise. In the con… ▽ More Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain. In contrast, image-level annotations, where only the presence of lesion is marked, are generally cheap, generated in far larger volumes compared to pixel-level labels, and contain less labeling noise. In the context of brain tumor segmentation, both pixel-level and image-level annotations are commonly available; thus, a natural question arises whether a segmentation procedure could take advantage of both. In the present work we: 1) propose a learning-based framework that allows simultaneous usage of both pixel- and image-level annotations in MRI images to learn a segmentation model for brain tumor; 2) study the influence of comparative amounts of pixel- and image-level annotations on the quality of brain tumor segmentation; 3) compare our approach to the traditional fully-supervised approach and show that the performance of our method in terms of segmentation quality may be competitive. △ Less

Submitted 6 November, 2019; v1 submitted 5 November, 2019; originally announced November 2019.

Comments: Accepted to IEEE International Conference on Machine Learning and Applications (ICMLA 2019). Typos corrected, images updated

A Method for Estimating the Proximity of Vector Representation Groups in Multidimensional Space. On the Example of the Paraphrase Task

Authors: Artem Artemov, Boris Alekseev

Abstract: The following paper presents a method of comparing two sets of vectors. The method can be applied in all tasks, where it is necessary to measure the closeness of two objects presented as sets of vectors. It may be applicable when we compare the meanings of two sentences as part of the problem of paraphrasing. This is the problem of measuring semantic similarity of two sentences (group of words). T… ▽ More The following paper presents a method of comparing two sets of vectors. The method can be applied in all tasks, where it is necessary to measure the closeness of two objects presented as sets of vectors. It may be applicable when we compare the meanings of two sentences as part of the problem of paraphrasing. This is the problem of measuring semantic similarity of two sentences (group of words). The existing methods are not sensible for the word order or syntactic connections in the considered sentences. The method appears to be advantageous because it neither presents a group of words as one scalar value, nor does it try to show the closeness through an aggregation vector, which is mean for the set of vectors. Instead of that we measure the cosine of the angle as the mean for the first group vectors projections (the context) on one side and each vector of the second group on the other side. The similarity of two sentences defined by these means does not lose any semantic characteristics and takes account of the words traits. The method was verified on the comparison of sentence pairs in Russian. △ Less

Submitted 29 August, 2019; v1 submitted 25 August, 2019; originally announced August 2019.

Comments: 8 pages, 1 figure, 2 tables

ACM Class: I.2.6; I.2.7

Learning to Approximate Directional Fields Defined over 2D Planes

Authors: Maria Taktasheva, Albert Matveev, Alexey Artemov, Evgeny Burnaev

Abstract: Reconstruction of directional fields is a need in many geometry processing tasks, such as image tracing, extraction of 3D geometric features, and finding principal surface directions. A common approach to the construction of directional fields from data relies on complex optimization procedures, which are usually poorly formalizable, require a considerable computational effort, and do not transfer… ▽ More Reconstruction of directional fields is a need in many geometry processing tasks, such as image tracing, extraction of 3D geometric features, and finding principal surface directions. A common approach to the construction of directional fields from data relies on complex optimization procedures, which are usually poorly formalizable, require a considerable computational effort, and do not transfer across applications. In this work, we propose a deep learning-based approach and study the expressive power and generalization ability. △ Less

Submitted 1 July, 2019; originally announced July 2019.

Comments: 7 pages, 5 figures

Journal ref: Proc. of AIST, 2019

Approximate multiplication of nearly sparse matrices with decay in a fully recursive distributed task-based parallel framework

Authors: Anton G. Artemov

Abstract: In this paper we consider parallel implementations of approximate multiplication of large matrices with exponential decay of elements. Such matrices arise in computations related to electronic structure calculations and some other fields of computational science. Commonly, sparsity is introduced by dropping out small entries (truncation) of input matrices. Another approach, the sparse approximate… ▽ More In this paper we consider parallel implementations of approximate multiplication of large matrices with exponential decay of elements. Such matrices arise in computations related to electronic structure calculations and some other fields of computational science. Commonly, sparsity is introduced by dropping out small entries (truncation) of input matrices. Another approach, the sparse approximate multiplication algorithm [M. Challacombe and N. Bock, arXiv preprint 1011.3534, 2010] performs truncation of sub-matrix products. We consider these two methods and their combination, i.e. truncation of both input matrices and sub-matrix products. Implementations done using the Chunks and Tasks programming model and library [E. H. Rubensson and E. Rudberg, Parallel Comput., 40:328-343, 2014] are presented and discussed. We show that the absolute error in the Frobenius norm behaves as $O\left(n^{1/2} \right), n \longrightarrow \infty $ and $O\left(τ^{p/2} \right), τ\longrightarrow 0,\,\, \forall p < 2$ for all three methods, where $n$ is the matrix size and $τ$ is the truncation threshold. We compare the methods on a model problem and show that the combined method outperforms the original two. The methods are also applied to matrices coming from large chemical systems with $\sim 10^6$ atoms. We show that the combination of the two methods achieves better weak scaling by reducing the amount of communication by a factor of $\approx 2$. △ Less

Submitted 20 February, 2021; v1 submitted 19 June, 2019; originally announced June 2019.

Comments: 26 pages, 6 figures

MSC Class: 65Y05; 65Y20; 65F50 ACM Class: G.1.0; D.1.3

Neural Network-based Object Classification by Known and Unknown Features (Based on Text Queries)

Authors: A. Artemov, I. Bolokhov, D. Kem, I. Khasenevich

Abstract: The article presents a method that improves the quality of classification of objects described by a combination of known and unknown features. The method is based on modernized Informational Neurobayesian Approach with consideration of unknown features. The proposed method was developed and trained on 1500 text queries of Promobot users in Russian to classify them into 20 categories (classes). As… ▽ More The article presents a method that improves the quality of classification of objects described by a combination of known and unknown features. The method is based on modernized Informational Neurobayesian Approach with consideration of unknown features. The proposed method was developed and trained on 1500 text queries of Promobot users in Russian to classify them into 20 categories (classes). As a result, the use of the method allowed to completely solve the problem of misclassification for queries with combining known and unknown features of the model. The theoretical substantiation of the method is presented by the formulated and proved theorem On the Model with Limited Knowledge. It states, that in conditions of limited data, an equal number of equally unknown features of an object cannot have different significance for the classification problem. △ Less

Submitted 3 June, 2019; originally announced June 2019.

Comments: 7 pages, 3 figures, 2 tables

ACM Class: I.2.6; I.2.7

Procedural Synthesis of Remote Sensing Images for Robust Change Detection with Neural Networks

Authors: Maria Kolos, Anton Marin, Alexey Artemov, Evgeny Burnaev

Abstract: Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant. However, in some instances, such as change detection in remote sensing images, annotated data cannot be obtained in sufficient quantities. In this work, we propose a simple and efficient method for creating realistic targ… ▽ More Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant. However, in some instances, such as change detection in remote sensing images, annotated data cannot be obtained in sufficient quantities. In this work, we propose a simple and efficient method for creating realistic targeted synthetic datasets in the remote sensing domain, leveraging the opportunities offered by game development engines. We provide a description of the pipeline for procedural geometry generation and rendering as well as an evaluation of the efficiency of produced datasets in a change detection scenario. Our evaluations demonstrate that our pipeline helps to improve the performance and convergence of deep learning models when the amount of real-world data is severely limited. △ Less

Submitted 20 May, 2019; originally announced May 2019.

Comments: 17 pages, 11 figures

Journal ref: 16th International Symposium on Neural Networks, ISNN 2019

Monocular 3D Object Detection via Geometric Reasoning on Keypoints

Authors: Ivan Barabanau, Alexey Artemov, Evgeny Burnaev, Vyacheslav Murashkin

Abstract: Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D detections. In this paper, we propose a novel keypoint-based approach for 3D object detection and localization from a single RGB image. We build our multi-branch model… ▽ More Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D detections. In this paper, we propose a novel keypoint-based approach for 3D object detection and localization from a single RGB image. We build our multi-branch model around 2D keypoint detection in images and complement it with a conceptually simple geometric reasoning method. Our network performs in an end-to-end manner, simultaneously and interdependently estimating 2D characteristics, such as 2D bounding boxes, keypoints, and orientation, along with full 3D pose in the scene. We fuse the outputs of distinct branches, applying a reprojection consistency loss during training. The experimental evaluation on the challenging KITTI dataset benchmark demonstrates that our network achieves state-of-the-art results among other monocular 3D detectors. △ Less

Submitted 14 May, 2019; originally announced May 2019.

Parallelization and scalability analysis of inverse factorization using the Chunks and Tasks programming model

Authors: Anton G. Artemov, Elias Rudberg, Emanuel H. Rubensson

Abstract: We present three methods for distributed memory parallel inverse factorization of block-sparse Hermitian positive definite matrices. The three methods are a recursive variant of the AINV inverse Cholesky algorithm, iterative refinement, and localized inverse factorization, respectively. All three methods are implemented using the Chunks and Tasks programming model, building on the distributed spar… ▽ More We present three methods for distributed memory parallel inverse factorization of block-sparse Hermitian positive definite matrices. The three methods are a recursive variant of the AINV inverse Cholesky algorithm, iterative refinement, and localized inverse factorization, respectively. All three methods are implemented using the Chunks and Tasks programming model, building on the distributed sparse quad-tree matrix representation and parallel matrix-matrix multiplication in the publicly available Chunks and Tasks Matrix Library (CHTML). Although the algorithms are generally applicable, this work was mainly motivated by the need for efficient and scalable inverse factorization of the basis set overlap matrix in large scale electronic structure calculations. We perform various computational tests on overlap matrices for quasi-linear Glutamic Acid-Alanine molecules and three-dimensional water clusters discretized using the standard Gaussian basis set STO-3G with up to more than 10 million basis functions. We show that for such matrices the computational cost increases only linearly with system size for all the three methods. We show both theoretically and in numerical experiments that the methods based on iterative refinement and localized inverse factorization outperform previous parallel implementations in weak scaling tests where the system size is increased in direct proportion to the number of processes. We show also that compared to the method based on pure iterative refinement the localized inverse factorization requires much less communication. △ Less

Submitted 24 January, 2019; v1 submitted 23 January, 2019; originally announced January 2019.

Comments: 20 pages, 7 figures, corrected the author list

MSC Class: 65Y05; 65F30; 65F50 ACM Class: D.1.3; G.1.3

Perceptual deep depth super-resolution

Authors: Oleg Voynov, Alexey Artemov, Vage Egiazarian, Alexander Notchenko, Gleb Bobrovskikh, Denis Zorin, Evgeny Burnaev

Abstract: RGBD images, combining high-resolution color and lower-resolution depth from various types of depth sensors, are increasingly common. One can significantly improve the resolution of depth maps by taking advantage of color information; deep learning methods make combining color and depth information particularly easy. However, fusing these two sources of data may lead to a variety of artifacts. If… ▽ More RGBD images, combining high-resolution color and lower-resolution depth from various types of depth sensors, are increasingly common. One can significantly improve the resolution of depth maps by taking advantage of color information; deep learning methods make combining color and depth information particularly easy. However, fusing these two sources of data may lead to a variety of artifacts. If depth maps are used to reconstruct 3D shapes, e.g., for virtual reality applications, the visual quality of upsampled images is particularly important. The main idea of our approach is to measure the quality of depth map upsampling using renderings of resulting 3D surfaces. We demonstrate that a simple visual appearance-based loss, when used with either a trained CNN or simply a deep prior, yields significantly improved 3D shapes, as measured by a number of existing perceptual metrics. We compare this approach with a number of existing optimization and learning-based techniques. △ Less

Submitted 9 September, 2019; v1 submitted 24 December, 2018; originally announced December 2018.

Comments: 26 pages

ABC: A Big CAD Model Dataset For Geometric Deep Learning

Authors: Sebastian Koch, Albert Matveev, Zhongshi Jiang, Francis Williams, Alexey Artemov, Evgeny Burnaev, Marc Alexa, Denis Zorin, Daniele Panozzo

Abstract: We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing ground truth for differential quantities, patch segmentation, geometric feature detection, and shape reconstruction. Sampling the parametric descriptions of sur… ▽ More We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing ground truth for differential quantities, patch segmentation, geometric feature detection, and shape reconstruction. Sampling the parametric descriptions of surfaces and curves allows generating data in different formats and resolutions, enabling fair comparisons for a wide range of geometric learning algorithms. As a use case for our dataset, we perform a large-scale benchmark for estimation of surface normals, comparing existing data driven methods and evaluating their performance against both the ground truth and traditional normal estimation methods. △ Less

Submitted 30 April, 2019; v1 submitted 14 December, 2018; originally announced December 2018.

Comments: 15 pages

fMRI: preprocessing, classification and pattern recognition

Authors: Maxim Sharaev, Alexander Andreev, Alexey Artemov, Alexander Bernstein, Evgeny Burnaev, Ekaterina Kondratyeva, Svetlana Sushchinskaya, Renat Akzhigitov

Abstract: As machine learning continues to gain momentum in the neuroscience community, we witness the emergence of novel applications such as diagnostics, characterization, and treatment outcome prediction for psychiatric and neurological disorders, for instance, epilepsy and depression. Systematic research into these mental disorders increasingly involves drawing clinical conclusions on the basis of data-… ▽ More As machine learning continues to gain momentum in the neuroscience community, we witness the emergence of novel applications such as diagnostics, characterization, and treatment outcome prediction for psychiatric and neurological disorders, for instance, epilepsy and depression. Systematic research into these mental disorders increasingly involves drawing clinical conclusions on the basis of data-driven approaches; to this end, structural and functional neuroimaging serve as key source modalities. Identification of informative neuroimaging markers requires establishing a comprehensive preparation pipeline for data which may be severely corrupted by artifactual signal fluctuations. In this work, we review a large body of literature to provide ample evidence for the advantages of pattern recognition approaches in clinical applications, overview advanced graph-based pattern recognition approaches, and propose a noise-aware neuroimaging data processing pipeline. To demonstrate the effectiveness of our approach, we provide results from a pilot study, which show a significant improvement in classification accuracy, indicating a promising research direction. △ Less

Submitted 26 April, 2018; originally announced April 2018.

Comments: 20 pages, 1 figure

Machine Learning pipeline for discovering neuroimaging-based biomarkers in neurology and psychiatry

Authors: Alexander Bernstein, Evgeny Burnaev, Ekaterina Kondratyeva, Svetlana Sushchinskaya, Maxim Sharaev, Alexander Andreev, Alexey Artemov, Renat Akzhigitov

Abstract: We consider a problem of diagnostic pattern recognition/classification from neuroimaging data. We propose a common data analysis pipeline for neuroimaging-based diagnostic classification problems using various ML algorithms and processing toolboxes for brain imaging. We illustrate the pipeline application by discovering new biomarkers for diagnostics of epilepsy and depression based on clinical an… ▽ More We consider a problem of diagnostic pattern recognition/classification from neuroimaging data. We propose a common data analysis pipeline for neuroimaging-based diagnostic classification problems using various ML algorithms and processing toolboxes for brain imaging. We illustrate the pipeline application by discovering new biomarkers for diagnostics of epilepsy and depression based on clinical and MRI/fMRI data for patients and healthy volunteers. △ Less

Submitted 26 April, 2018; originally announced April 2018.

Comments: 20 pages, 2 figures

The Training of Neuromodels for Machine Comprehension of Text. Brain2Text Algorithm

Authors: A. Artemov, A. Sergeev, A. Khasenevich, A. Yuzhakov, M. Chugunov

Abstract: Nowadays, the Internet represents a vast informational space, growing exponentially and the problem of search for relevant data becomes essential as never before. The algorithm proposed in the article allows to perform natural language queries on content of the document and get comprehensive meaningful answers. The problem is partially solved for English as SQuAD contains enough data to learn on,… ▽ More Nowadays, the Internet represents a vast informational space, growing exponentially and the problem of search for relevant data becomes essential as never before. The algorithm proposed in the article allows to perform natural language queries on content of the document and get comprehensive meaningful answers. The problem is partially solved for English as SQuAD contains enough data to learn on, but there is no such dataset in Russian, so the methods used by scientists now are not applicable to Russian. Brain2 framework allows to cope with the problem - it stands out for its ability to be applied on small datasets and does not require impressive computing power. The algorithm is illustrated on Sberbank of Russia Strategy's text and assumes the use of a neuromodel consisting of 65 mln synapses. The trained model is able to construct word-by-word answers to questions based on a given text. The existing limitations are its current inability to identify synonyms, pronoun relations and allegories. Nevertheless, the results of conducted experiments showed high capacity and generalisation ability of the suggested approach. △ Less

Submitted 30 March, 2018; originally announced April 2018.

Comments: 5 pages, 2 figures, 6 tables

ACM Class: I.2.6; I.2.7

Informational Neurobayesian Approach to Neural Networks Training. Opportunities and Prospects

Authors: Artem Artemov, Eugeny Lutsenko, Edward Ayunts, Ivan Bolokhov

Abstract: A study of the classification problem in context of information theory is presented in the paper. Current research in that field is focused on optimisation and bayesian approach. Although that gives satisfying results, they require a vast amount of data and computations to train on. Authors propose a new concept named Informational Neurobayesian Approach (INA), which allows to solve the same probl… ▽ More A study of the classification problem in context of information theory is presented in the paper. Current research in that field is focused on optimisation and bayesian approach. Although that gives satisfying results, they require a vast amount of data and computations to train on. Authors propose a new concept named Informational Neurobayesian Approach (INA), which allows to solve the same problems, but requires significantly less training data as well as computational power. Experiments were conducted to compare its performance with the traditional one and the results showed that capacity of the INA is quite promising. △ Less

Submitted 3 December, 2017; v1 submitted 19 October, 2017; originally announced October 2017.

Comments: 9 pages, 5 figures, 2 tables; corrected typos, mistake in a formula

ACM Class: I.2.6; I.2.7

Event Index - an LHCb Event Search System

Authors: Andrey Ustyuzhanin, Alexey Artemov, Nikita Kazeev, Artem Redkin

Abstract: During LHC Run 1, the LHCb experiment recorded around $10^{11}$ collision events. This paper describes Event Index - an event search system. Its primary function is to quickly select subsets of events from a combination of conditions, such as the estimated decay channel or number of hits in a subdetector. Event Index is essentially Apache Lucene optimized for read-only indexes distributed over ind… ▽ More During LHC Run 1, the LHCb experiment recorded around $10^{11}$ collision events. This paper describes Event Index - an event search system. Its primary function is to quickly select subsets of events from a combination of conditions, such as the estimated decay channel or number of hits in a subdetector. Event Index is essentially Apache Lucene optimized for read-only indexes distributed over independent shards on independent nodes. △ Less

Submitted 26 October, 2015; v1 submitted 27 May, 2015; originally announced May 2015.

Comments: Report for the proceedings of the CHEP-2015 conference

Journal ref: Journal of Physics: Conference Series, vol. 664, num 3, pages 032019, 2015