Research map / Video / Action recognition
Human Action Recognition From Various Data Modalities: A Review
Zehua Sun, Qiuhong Ke, Hossein Rahmani, Mohammed Bennamoun, Gang Wang, Jun Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| move from skeleton RNN (Trust Gate ST-LSTM) to graph convolution (InfoGCN) | skeleton HAR · NTU RGB+D (cross-subject) | accuracy: 69.2 -> 93.0 | Improved |
| move from ST-GCN to CTR-GCN | skeleton GCN · NTU RGB+D (cross-subject) | accuracy: 81.5 -> 92.4 | Improved |
| add Transformer attention to skeleton models (ST-TR vs ST-GCN style) | skeleton HAR · NTU RGB+D (cross-subject) | accuracy: 89.9 -> 92.3 | Mixed |
| move from NL I3D to Transformer MTV-H | RGB video HAR · Kinetics-400 | accuracy: 77.7 -> 89.1 | Improved |
| use 3D CNN with BERT head instead of two-stream 2D CNN (TSN) | RGB video HAR · UCF101 | accuracy: 94.2 -> 98.7 | Improved |
| use RNN-based DB-LSTM instead of Soft Attention Model | RGB video HAR · HMDB51 | accuracy: 41.3 -> 81.2 | Improved |
Closest papers by meaning
- Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms (IJCV 2026 · similarity 0.90)
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.88)
- MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos (TPAMI 2022 · similarity 0.88)
- DarkShake-DVS: Event-based Human Action Recognition under Low-light and Shaking Camera Conditions (CVPR 2026 · similarity 0.88)
- Human Action Recognition and Prediction: A Survey (IJCV 2022 · similarity 0.87)
- HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization (ICCV 2019 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
