Research map / Detection and segmentation / Open-set and few-shot detection
Transferable Interactiveness Knowledge for Human-Object Interaction Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 a jointly trained interactiveness predictor | HOI detection on HICO-DET · HICO-DET Default Full | mAP: 13.75 -> 17.03 | Helped |
| Train the interactiveness predictor using both HICO-DET and V-COCO | HOI detection on HICO-DET · HICO-DET Default Full | mAP: 16.91 -> 17.22 | Helped |
| Transfer interactiveness predictor knowledge from HICO-DET to V-COCO | HOI detection on V-COCO · V-COCO | AP_role: 43.2 -> 48.3 | Helped |
| Transfer HOI classifier knowledge across datasets | HOI detection on HICO-DET and V-COCO · HICO-DET and V-COCO | mAP / AP_role: 13.75 -> 10.61; 43.2 -> 38.5 | Hurt |
| Add Non-Interaction Suppression at test time (ablation) | R P_D C_D · HICO-DET Default Full | mAP: 15.86 -> 17.03 | Helped |
| Add Non-Interaction Suppression at test time (ablation) | R P_D C_D · V-COCO | AP_role: 46.2 -> 47.8 | Helped |
| Add Low-grade Instance Suppressive weighting (ablation) | R P_D C_D · HICO-DET Default Full | mAP: 16.35 -> 17.03 | Helped |
| Add Low-grade Instance Suppressive weighting (ablation) | R P_D C_D · V-COCO | AP_role: 47.4 -> 47.8 | Helped |
| Add both Non-Interaction Suppression and Low-grade Instance Suppressive weighting (ablation) | R P_D C_D · HICO-DET Default Full | mAP: 15.45 -> 17.03 | Helped |
| Add both Non-Interaction Suppression and Low-grade Instance Suppressive weighting (ablation) | R P_D C_D · V-COCO | AP_role: 45.8 -> 47.8 | Helped |
| Use human, object, and spatial-pose streams together instead of only the human stream (ablation) | Interactiveness network · HICO-DET Default Full | mAP: 14.91 -> 17.03 | Helped |
| Use human, object, and spatial-pose streams together instead of only the object stream (ablation) | Interactiveness network · HICO-DET Default Full | mAP: 15.28 -> 17.03 | Helped |
Closest papers by meaning
- Interactiveness Field in Human-Object Interactions (CVPR 2022 · similarity 0.91)
- Learning Transferable Human-Object Interaction Detector With Natural Language Supervision (CVPR 2022 · 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)
- Exploring Pose-Aware Human-Object Interaction via Hybrid Learning (CVPR 2024 · similarity 0.88)
- HOIMamba: Efficient Mamba-based Disentangled Progressive Learning for HOI Detection (AAAI 2025 · 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.