Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)
Not on the map. Why?
Abstract (arXiv)
Graph convolutional networks (GCNs) are an effective skeleton-based human action recognition (HAR) technique. GCNs enable the specification of CNNs to a non-Euclidean frame that is more flexible. The previous GCN-based models still have a lot of issues: (I) The graph structure is the same for all model layers and input data.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 66 references that are in the map. First posted on arXiv 10 Nov 2024.
Builds on
34 of 66 references.
References · 34
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017The Kinetics Human Action Video Datasetcited by 1,909
- 2018SlowFast Networks for Video Recognitioncited by 1,867
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
- 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
- 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
- 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
- 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
- 2017Residual Attention Network for Image Classificationcited by 386
- 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
22 more
- 2018Neural Relational Inference for Interacting Systemscited by 339
- 2016Learning Convolutional Neural Networks for Graphscited by 314
- 2021Revisiting Skeleton-based Action Recognitioncited by 257
- 2018Videos as Space-Time Region Graphscited by 221
- 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 143
- 2018Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNNcited by 143
- 2018Gather-Excite: Exploiting Feature Context in Convolutional Neural Networkscited by 139
- 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 126
- 20182D/3D Pose Estimation and Action Recognition using Multitask Deep Learningcited by 103
- 2017Interpretable 3D Human Action Analysis with Temporal Convolutional Networkscited by 89
- 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
- 2021Elaborative Rehearsal for Zero-shot Action Recognitioncited by 77
- 2019Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searchingcited by 70
- 2017Skeleton-based Action Recognition with Convolutional Neural Networkscited by 54
- 2017Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detectioncited by 34
- 2018Glimpse Clouds: Human Activity Recognition from Unstructured Feature Pointscited by 33
- 2016Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videoscited by 26
- 2023Unified Keypoint-based Action Recognition Framework via Structured Keypoint Poolingcited by 19
- 2020Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognitioncited by 8
- 2020Temporal Attention-Augmented Graph Convolutional Network for Efficient Skeleton-Based Human Action Recognitioncited by 8
- 2022Bootstrapped Representation Learning for Skeleton-Based Action Recognitioncited by 8
- 2021Skeleton-Split Framework using Spatial Temporal Graph Convolutional Networks for Action Recogntioncited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.