Research map / Detection and segmentation / Open-set and few-shot detection
Exploiting Scene Graphs for Human-Object Interaction Detection
Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li
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 scene graph embedding (ablation) | baseline · V-COCO | mAP_role: 46.5 -> 49.3 | Improved |
| add relation-aware message passing (ablation) | baseline · V-COCO | mAP_role: 46.5 -> 50.2 | Improved |
| add image global feature (ablation) | relation-aware message passing model · V-COCO | mAP_role: 50.2 -> 51.1 | Improved |
| use scene graph embedding instead of image global feature (ablation) | relation-aware message passing model · V-COCO | mAP_role: 51.1 -> 52.8 | Improved |
| add non-relation-aware message passing (ablation) | scene graph embedding model · V-COCO | mAP_role: 49.3 -> 51.0 | Improved |
| use relation-aware instead of non-relation-aware message passing (ablation) | scene graph embedding model · V-COCO | mAP_role: 51.0 -> 52.8 | Improved |
| add scene graph embedding (ablation) | baseline · HICO-DET Default Full | mAP: 14.54 -> 17.27 | Improved |
| add relation-aware message passing (ablation) | baseline · HICO-DET Default Full | mAP: 14.54 -> 18.46 | Improved |
| use scene graph embedding instead of image global feature (ablation) | relation-aware message passing model · HICO-DET Default Full | mAP: 19.02 -> 20.62 | Improved |
| use relation-aware instead of non-relation-aware message passing (ablation) | scene graph embedding model · HICO-DET Default Full | mAP: 18.85 -> 20.62 | Improved |
| use relation-aware instead of non-relation-aware message passing (ablation) | scene graph embedding model · HICO-DET Known Object Full | mAP: 20.75 -> 23.48 | Improved |
| add both scene graph embedding and relation-aware message passing (ablation) | baseline · V-COCO | mAP_role: 46.5 -> 52.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- VSGNet — VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions (CVPR 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Human-Object Interaction as Groups (NeurIPS 2025 · similarity 0.92)
- Learning to Detect Human-Object Interactions With Knowledge (CVPR 2019 · similarity 0.92)
- ContextHOI: Spatial Context Learning for Human-Object Interaction Detection (AAAI 2025 · similarity 0.91)
- Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection (CVPR 2024 · similarity 0.89)
- Exploring Pose-Aware Human-Object Interaction via Hybrid Learning (CVPR 2024 · similarity 0.89)
- HORP: Human-Object Relation Priors Guided HOI Detection (CVPR 2025 · 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.
