Research map / Detection and segmentation / Open-set and few-shot detection
Geometric Features Informed Multi-Person Human-Object Interaction Recognition in Videos
Tanqiu Qiao, Qianhui Men, Frederick W. B. Li, Yoshiki Kubotani, Shigeo Morishima, Hubert P. H. Shum
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 geometric features (skeleton and object keypoints) fused with visual features, versus visual-only ASSIGN | ASSIGN · MPHOI | F1@10 sub-activity: 59.1 -> 68.6 | Improved |
| add geometric features fused with visual features, versus visual-only ASSIGN | ASSIGN · CAD-120 | F1@10 sub-activity: 88.0 -> 89.5 | Improved |
| add geometric features fused with visual features, versus ASSIGN | ASSIGN · Bimanual Actions | F1@10 sub-activity: 84.0 -> 85.0 | Improved |
| add human skeleton features to geometric-level graph (ablation) | 2G-GCN · CAD-120 | F1@10 sub-activity: 87.7 -> 89.5 | Improved |
| add object keypoint features to geometric-level graph (ablation) | 2G-GCN · CAD-120 | F1@10 sub-activity: 88.3 -> 89.5 | Improved |
| add the embedding function on geometric features (ablation) | 2G-GCN · CAD-120 | F1@10 sub-activity: 89.4 -> 89.5 | Improved |
| add similarity-based adaptive adjacency matrix in the GCN (ablation) | 2G-GCN · CAD-120 | F1@10 sub-activity: 88.7 -> 89.5 | Improved |
| add human-object attention connections in fusion-level graph (ablation) | 2G-GCN · CAD-120 | F1@10 sub-activity: 73.4 -> 89.5 | Improved |
| add object-object attention connections in fusion-level graph (ablation) | 2G-GCN · CAD-120 | F1@10 sub-activity: 88.3 -> 89.5 | Improved |
| add human-geometry connection to the fusion-level graph (ablation) | 2G-GCN · CAD-120 | F1@10 sub-activity: 89.5 -> 89.0 | Hurt |
| add human skeleton features to geometric-level graph (ablation) | 2G-GCN · CAD-120 | F1@10 object affordance: 91.0 -> 92.4 | Improved |
| add human-object attention connections in fusion-level graph (ablation) | 2G-GCN · CAD-120 | F1@10 object affordance: 90.3 -> 92.4 | Improved |
Closest papers by meaning
- Interaction-centric Spatio-Temporal Context Reasoning for Multi-Person Video HOI Recognition (ECCV 2024 · similarity 0.91)
- 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)
- Learning Human-Object Interaction as Groups (NeurIPS 2025 · similarity 0.88)
- HORP: Human-Object Relation Priors Guided HOI Detection (CVPR 2025 · similarity 0.88)
- Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection (AAAI 2024 · similarity 0.87)
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.
