English
Related papers

Related papers: E2E-GNet: An End-to-End Skeleton-based Geometric D…

200 papers

In modern computer vision, images are typically represented as a fixed uniform grid with some stride and processed via a deep convolutional neural network. We argue that deforming the grid to better align with the high-frequency image…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Jun Gao , Zian Wang , Jinchen Xuan , Sanja Fidler

This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single image, KeypointNet extracts 3D keypoints that are optimized…

Computer Vision and Pattern Recognition · Computer Science 2018-11-26 Supasorn Suwajanakorn , Noah Snavely , Jonathan Tompson , Mohammad Norouzi

Convolutional Neural Networks (CNNs) achieve impressive performance in a wide variety of fields. Their success benefited from a massive boost when very deep CNN models were able to be reliably trained. Despite their merits, CNNs fail to…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Guohao Li , Matthias Müller , Ali Thabet , Bernard Ghanem

We present a PDE-based framework that generalizes Group equivariant Convolutional Neural Networks (G-CNNs). In this framework, a network layer is seen as a set of PDE-solvers where geometrically meaningful PDE-coefficients become the…

Machine Learning · Computer Science 2022-08-24 Bart Smets , Jim Portegies , Erik Bekkers , Remco Duits

Skeleton-based action recognition has gained considerable traction thanks to its utilization of succinct and robust skeletal representations. Nonetheless, current methodologies often lean towards utilizing a solitary backbone to model…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Jinfu Liu , Baiqiao Yin , Jiaying Lin , Jiajun Wen , Yue Li , Mengyuan Liu

Incorporating Euclidean symmetries (e.g. rotation equivariance) as inductive biases into graph neural networks has improved their generalization ability and data efficiency in unbounded physical dynamics modeling. However, in various…

Machine Learning · Computer Science 2024-06-25 Zinan Zheng , Yang Liu , Jia Li , Jianhua Yao , Yu Rong

Deep generative models provide flexible frameworks for modeling complex, structured data such as images, videos, 3D objects, and texts. However, when applied to sequences of human skeletons, standard variational autoencoders (VAEs) often…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Arafat Rahman , Shashwat Kumar , Laura E. Barnes , Anuj Srivastava

Dual energy X-ray Computed Tomography (DECT) enables to automatically decompose materials in clinical images without the manual segmentation using the dependency of the X-ray linear attenuation with energy. In this work we propose a deep…

Image and Video Processing · Electrical Eng. & Systems 2024-06-04 Jiandong Wang , Alessandro Perelli

Graph convolutional networks (GCNs), which generalize CNNs to more generic non-Euclidean structures, have achieved remarkable performance for skeleton-based action recognition. However, there still exist several issues in the previous…

Computer Vision and Pattern Recognition · Computer Science 2020-12-02 Lei Shi , Yifan Zhang , Jian Cheng , Hanqing Lu

Skeleton-based action recognition has achieved remarkable performance with the development of graph convolutional networks (GCNs). However, most of these methods tend to construct complex topology learning mechanisms while neglecting the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Zeyu Liang , Hailun Xia , Naichuan Zheng , Huan Xu

This paper presents a novel method, named geodesic deformable networks (GDN), that for the first time enables the learning of geodesic flows of deformation fields derived from images. In particular, the capability of our proposed GDN being…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Nian Wu , Miaomiao Zhang

Learning complex network dynamics is fundamental for understanding, modeling, and controlling real-world complex systems. Though great efforts have been made to predict the future states of nodes on networks, the capability of capturing…

Social and Information Networks · Computer Science 2025-03-04 Ruikun Li , Huandong Wang , Jinghua Piao , Qingmin Liao , Yong Li

Skeleton-based action recognition has attracted considerable attention in computer vision since skeleton data is more robust to the dynamic circumstance and complicated background than other modalities. Recently, many researchers have used…

Computer Vision and Pattern Recognition · Computer Science 2020-03-18 Hao Yang , Dan Yan , Li Zhang , Dong Li , YunDa Sun , ShaoDi You , Stephen J. Maybank

Graph convolutional networks (GCNs) have been very successful in skeleton-based human action recognition where the sequence of skeletons is modeled as a graph. However, most of the GCN-based methods in this area train a deep feed-forward…

Computer Vision and Pattern Recognition · Computer Science 2021-04-28 Negar Heidari , Alexandros Iosifidis

We propose novel dynamic multiscale graph neural networks (DMGNN) to predict 3D skeleton-based human motions. The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion…

Computer Vision and Pattern Recognition · Computer Science 2020-03-20 Maosen Li , Siheng Chen , Yangheng Zhao , Ya Zhang , Yanfeng Wang , Qi Tian

Convolutional Neural Networks (CNNs) have been very successful at solving a variety of computer vision tasks such as object classification and detection, semantic segmentation, activity understanding, to name just a few. One key enabling…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Guohao Li , Matthias Müller , Guocheng Qian , Itzel C. Delgadillo , Abdulellah Abualshour , Ali Thabet , Bernard Ghanem

This paper presents a new framework for human action recognition from a 3D skeleton sequence. Previous studies do not fully utilize the temporal relationships between video segments in a human action. Some studies successfully used very…

Computer Vision and Pattern Recognition · Computer Science 2018-08-21 Thao Minh Le , Nakamasa Inoue , Koichi Shinoda

Human action recognition as an important application of computer vision has been studied for decades. Among various approaches, skeleton-based methods recently attract increasing attention due to their robust and superior performance.…

Computer Vision and Pattern Recognition · Computer Science 2021-02-26 Tingtian Li , Zixun Sun , Xiao Chen

We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure. Similar to finite element analysis, we assign nodes of a GNN to spatial locations and use a computational…

Machine Learning · Computer Science 2019-11-19 Ferran Alet , Adarsh K. Jeewajee , Maria Bauza , Alberto Rodriguez , Tomas Lozano-Perez , Leslie Pack Kaelbling

Geometric deep learning has been revolutionizing the molecular modeling field. Despite the state-of-the-art neural network models are approaching ab initio accuracy for molecular property prediction, their applications, such as drug…

Chemical Physics · Physics 2023-08-17 Yusong Wang , Shaoning Li , Xinheng He , Mingyu Li , Zun Wang , Nanning Zheng , Bin Shao , Tie-Yan Liu , Tong Wang
‹ Prev 1 3 4 5 6 7 10 Next ›