Research map / Video / Video-language understanding
Interaction-centric Spatio-Temporal Context Reasoning for Multi-Person Video HOI Recognition
Yisong Wang, Nan Xi, Jingjing Meng, Junsong Yuan
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 context fuser module (ablation) | Ours · MPHOI-72 | F1@10: 65.8 -> 91.6 | Improved |
| add interaction state reasoner (ablation) | Ours · MPHOI-72 | F1@10: 80.1 -> 91.6 | Improved |
| add interaction feature loss (ablation) | Ours · MPHOI-72 | F1@10: 73.5 -> 91.6 | Improved |
| use interaction-centric hypersphere instead of Euclidean distance (lambda = 0) (ablation) | Ours · CAD-120 | F1@10: 72.0 -> 90.7 | Improved |
| use interaction-centric hypersphere instead of MLP+Softmax classifier (ablation) | Ours · CAD-120 | F1@10: 79.5 -> 90.7 | Improved |
| use interaction-centric hypersphere instead of MLP+Softmax classifier (ablation) | Ours · MPHOI-72 | F1@10: 84.6 -> 91.6 | Improved |
| add CLIP and BLIP initialization of interaction and context features (ablation) | Ours · MPHOI-72 | F1@10: 80.0 -> 91.6 | Improved |
| add CLIP and BLIP initialization (ablation) | Ours · CAD-120 | F1@10: 89.4 -> 90.7 | No clear effect |
| add interaction state reasoner (ablation) | Ours · Bimanual Actions | F1@50: 73.0 -> 74.2 | Mixed |
| add context fuser (ablation) | Ours · Bimanual Actions | F1@50: 71.1 -> 74.2 | Mixed |
| Proposed method vs 2G-GCN | Ours · MPHOI-72 | F1@10: 68.6 -> 91.6 | Improved |
| Proposed method vs 2G-GCN on single-person data | Ours · Bimanual Actions | F1@10: 85.0 -> 85.0 | No clear effect |
Closest papers by meaning
- Geometric Features Informed Multi-Person Human-Object Interaction Recognition in Videos (ECCV 2022 · similarity 0.91)
- ContextHOI: Spatial Context Learning for Human-Object Interaction Detection (AAAI 2025 · similarity 0.90)
- Learning Human-Object Interaction as Groups (NeurIPS 2025 · similarity 0.89)
- HORP: Human-Object Relation Priors Guided HOI Detection (CVPR 2025 · similarity 0.89)
- HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment (CVPR 2024 · similarity 0.89)
- Exploring Pose-Aware Human-Object Interaction via Hybrid Learning (CVPR 2024 · similarity 0.89)
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.
