Research map / Detection and segmentation / Open-set and few-shot detection
Cascaded Human-Object Interaction Recognition
Tianfei Zhou, Wenguan Wang, Siyuan Qi, Haibin Ling, Jianbing Shen
Check 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 the cascade architecture (ablation) | C-HOI · PIC | R@20: 19.0 -> 27.8 | Improved |
| Add the cascade architecture (ablation) | C-HOI · HOIW | mAP_rel: 38.6 -> 43.7 | Improved |
| Add IHSM to the component-free baseline (ablation) | C-HOI · HOIW | mAP_rel: 33.9 -> 34.4 | Improved |
| Add EFRA to the component-free baseline (ablation) | C-HOI · HOIW | mAP_rel: 33.9 -> 36.7 | Improved |
| Add RRM to the IHSM + EFRA variant (ablation) | C-HOI · HOIW | mAP_rel: 37.5 -> 38.6 | Improved |
| Increase cascade stages from 1 to 2 (ablation) | C-HOI · PIC | R@20: 19.0 -> 25.5 | Improved |
| Increase cascade stages beyond 3 (ablation) | C-HOI · PIC | R@20: 27.8 -> 27.8 | No clear effect |
| Use visual features rather than semantic-only or geometric-only features (ablation) | C-HOI relation classifier · PIC | R@20: 14.5; 19.6; 22.2 | Improved |
| Fuse scores as (visual + geometric) × semantic instead of simple sum (ablation) | C-HOI relation classifier · PIC | R@20: 26.7 -> 27.8 | Improved |
| Use mask-based instead of bbox-based relation features (ablation) | C-HOI · PIC | R@20: 27.1 -> 27.8 | Improved |
| Add mask annotations to the bbox-trained V-COCO variant (ablation) | C-HOI · V-COCO test | mAP_role (%): 48.3 -> 48.9 | Improved |
| Use 5 cascade stages instead of 3 (ablation) | C-HOI · HOIW | mAP_rel: 43.7 -> 43.4 | Hurt |
Closest papers by meaning
- Cascaded Parsing of Human-Object Interaction Recognition (TPAMI 2021 · similarity 0.95)
- Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models (NeurIPS 2023 · similarity 0.92)
- HORP: Human-Object Relation Priors Guided HOI Detection (CVPR 2025 · similarity 0.90)
- Exploring Pose-Aware Human-Object Interaction via Hybrid Learning (CVPR 2024 · similarity 0.89)
- Learning Human-Object Interaction as Groups (NeurIPS 2025 · similarity 0.89)
- Toward Open-Set Human Object Interaction Detection (AAAI 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.
