Research map / Video / Action recognition
stagNet: An Attentive Semantic RNN for Group Activity Recognition
Mengshi Qi, Jie Qin, Annan Li, Yunhong Wang, Jiebo Luo, Luc Van Gool
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 |
|---|---|---|---|
| add spatio-temporal attention (proposal boxes) (ablation) | stagNet · Collective Activity | group accuracy: 85.6 -> 87.9 | Improved |
| add spatio-temporal attention (proposal boxes) (ablation) | stagNet · Volleyball | group accuracy: 85.7 -> 87.6 | Improved |
| add spatio-temporal attention (ground-truth boxes) (ablation) | stagNet · Collective Activity | group accuracy: 87.7 -> 89.1 | Improved |
| add spatio-temporal attention (ground-truth boxes) (ablation) | stagNet · Volleyball | group accuracy: 87.9 -> 89.3 | Improved |
| use ground-truth boxes instead of proposal boxes | stagNet · Collective Activity | group accuracy: 87.9 -> 89.1 | Improved |
| use ground-truth boxes instead of proposal boxes | stagNet · Volleyball | personal action accuracy: 79.6 -> 81.9 | Improved |
| use semantic graph structural RNN instead of person-level pooled VGG-16 features | stagNet · Collective Activity | group accuracy: 71.2 -> 87.9 | Improved |
| use semantic graph structural RNN instead of person-level pooled LRCN features | stagNet · Volleyball | group accuracy: 67.6 -> 87.6 | Improved |
Closest papers by meaning
- Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition (CVPR 2016 · similarity 0.89)
- GroupFormer: Group Activity Recognition With Clustered Spatial-Temporal Transformer (ICCV 2021 · similarity 0.88)
- Empowering Relational Network by Self-Attention Augmented Conditional Random Fields for Group Activity Recognition (ECCV 2020 · similarity 0.88)
- Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos (ECCV 2020 · similarity 0.88)
- SBGAR: Semantics Based Group Activity Recognition (ICCV 2017 · similarity 0.88)
- Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph (ECCV 2024 · similarity 0.88)
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.
