English
Related papers

Related papers: STEP CATFormer: Spatial-Temporal Effective Body-Pa…

200 papers

The dominant paradigm for video-based action segmentation is composed of two steps: first, for each frame, compute low-level features using Dense Trajectories or a Convolutional Neural Network that encode spatiotemporal information locally,…

Computer Vision and Pattern Recognition · Computer Science 2016-08-31 Colin Lea , Rene Vidal , Austin Reiter , Gregory D. Hager

Skeleton-based action recognition has gained significant attention for its ability to efficiently represent spatiotemporal information in a lightweight format. Most existing approaches use graph-based models to process skeleton sequences,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Jushang Qiu , Lei Wang

Graph convolutional networks (GCNs) aim at extending deep learning to arbitrary irregular domains, namely graphs. Their success is highly dependent on how the topology of input graphs is defined and most of the existing GCN architectures…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Hichem Sahbi

Many skeletal action recognition models use GCNs to represent the human body by 3D body joints connected body parts. GCNs aggregate one- or few-hop graph neighbourhoods, and ignore the dependency between not linked body joints. We propose…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Lei Wang , Piotr Koniusz

Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition. However, the application of prior graph-based methods, which predominantly employ whole temporal sequences as their input, to the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Lukas Hedegaard , Negar Heidari , Alexandros Iosifidis

The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. Existing approaches typically employ a single neural…

Computer Vision and Pattern Recognition · Computer Science 2021-08-11 Tailin Chen , Desen Zhou , Jian Wang , Shidong Wang , Yu Guan , Xuming He , Errui Ding

In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required. To solve these…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Dasom Ahn , Sangwon Kim , Hyunsu Hong , Byoung Chul Ko

Human Action Recognition (HAR) is an interesting research area in human-computer interaction used to monitor the activities of elderly and disabled individuals affected by physical and mental health. In the recent era, skeleton-based HAR…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Faisal Mehmood , Enqing Chen , Touqeer Abbas , Samah M. Alzanin

In skeleton-based action recognition, Graph Convolutional Networks model human skeletal joints as vertices and connect them through an adjacency matrix, which can be seen as a local attention mask. However, in most existing Graph…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Hao Xing , Darius Burschka

At present, people usually use some methods based on convolutional neural networks (CNNs) for Electroencephalograph (EEG) decoding. However, CNNs have limitations in perceiving global dependencies, which is not adequate for common EEG…

Signal Processing · Electrical Eng. & Systems 2021-06-23 Yonghao Song , Xueyu Jia , Lie Yang , Longhan Xie

Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Jiahui Wang , Zhenyou Wang , Shanna Zhuang , Hui Wang

Traffic forecasting is one of the most fundamental problems in transportation science and artificial intelligence. The key challenge is to effectively model complex spatial-temporal dependencies and correlations in modern traffic data.…

Machine Learning · Computer Science 2023-02-28 Haiyang Liu , Chunjiang Zhu , Detian Zhang , Qing Li

Skeleton-based action recognition task is entangled with complex spatio-temporal variations of skeleton joints, and remains challenging for Recurrent Neural Networks (RNNs). In this work, we propose a temporal-then-spatial recalibration…

Computer Vision and Pattern Recognition · Computer Science 2018-05-04 Chunyu Xie , Ce Li , Baochang Zhang , Chen Chen , Jungong Han , Changqing Zou , Jianzhuang Liu

Previous methods for skeleton-based gesture recognition mostly arrange the skeleton sequence into a pseudo picture or spatial-temporal graph and apply deep Convolutional Neural Network (CNN) or Graph Convolutional Network (GCN) for feature…

Computer Vision and Pattern Recognition · Computer Science 2021-06-28 Jianbo Liu , Ying Wang , Shiming Xiang , Chunhong Pan

Action recognition is a key algorithmic part of emerging on-the-edge smart video surveillance and security systems. Skeleton-based action recognition is an attractive approach which, instead of using RGB pixel data, relies on human pose…

Computer Vision and Pattern Recognition · Computer Science 2022-01-19 Justin Sanchez , Christopher Neff , Hamed Tabkhi

With the prevalence of accessible depth sensors, dynamic human body skeletons have attracted much attention as a robust modality for action recognition. Previous methods model skeletons based on RNN or CNN, which has limited expressive…

Computer Vision and Pattern Recognition · Computer Science 2019-04-16 Xiang Gao , Wei Hu , Jiaxiang Tang , Jiaying Liu , Zongming Guo

The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting local spatiotemporal…

Computer Vision and Pattern Recognition · Computer Science 2016-11-17 Colin Lea , Michael D. Flynn , Rene Vidal , Austin Reiter , Gregory D. Hager

For multimodal skeleton-based action recognition, Graph Convolutional Networks (GCNs) are effective models. Still, their reliance on floating-point computations leads to high energy consumption, limiting their applicability in…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Naichuan Zheng , Yuchen Du , Hailun Xia , Zeyu Liang

Skeleton-based action recognition has achieved remarkable results in human action recognition with the development of graph convolutional networks (GCNs). However, the recent works tend to construct complex learning mechanisms with…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Dongjingdin Liu , Pengpeng Chen , Miao Yao , Yijing Lu , Zijie Cai , Yuxin Tian

Graph convolution networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. However, previous GCN-based methods rely on elaborate human priors excessively and construct complex feature aggregation…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Shaojie Zhang , Jianqin Yin , Yonghao Dang , Jiajun Fu