Research map / Detection and segmentation / Open-set and few-shot detection
Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection
Yichao Cao, Qingfei Tang, Feng Yang, Xiu Su, Shan You, Xiaobo Lu, Chang Xu
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 Interactive Relation Encoder (IRE) to plain model (ablation) | plain two-stage HOI detector · V-COCO | AP_role #1: 58.51 -> 61.13 | Improved |
| add sentence- and word-level cross-modal alignment to IRE model (ablation) | RmLR · V-COCO | AP_role #1: 61.13 -> 63.78 | Improved |
| add word-level alignment (ablation) | RmLR · V-COCO | AP_role #1: 62.37 -> 63.78 | Improved |
| add sentence-level alignment (ablation) | RmLR · V-COCO | AP_role #1: 63.33 -> 63.78 | Improved |
| add knowledge transfer for IRM (ablation) | RmLR · V-COCO | AP_role #1: 62.53 -> 63.78 | Improved |
| add knowledge transfer for IRE (ablation) | RmLR · V-COCO | AP_role #1: 63.42 -> 63.78 | Improved |
| use BERT-large instead of ALBERT-base-v2 text encoder (ablation) | RmLR · V-COCO | AP_role #1: 63.45 -> 63.93 | Improved |
| vary loss term weights (ablation) | RmLR · V-COCO | AP_role #1: 62.73 to 63.69 | No clear effect |
| add linguistic knowledge transfer to two-stage detector | UPT-style detector · HICO-DET Default Full | mAP: 32.31 -> 37.41 | Improved |
| add RmLR modules to detector | UPT · V-COCO | FPS: 27.5 -> 27.2 | Hurt |
Closest papers by meaning
- Discovering Syntactic Interaction Clues for Human-Object Interaction Detection (CVPR 2024 · similarity 0.92)
- Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection (CVPR 2024 · similarity 0.91)
- Open-World Human-Object Interaction Detection via Multi-modal Prompts (CVPR 2024 · similarity 0.91)
- Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models (NeurIPS 2024 · similarity 0.91)
- SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection (CVPR 2025 · similarity 0.90)
- Toward Open-Set Human Object Interaction Detection (AAAI 2024 · similarity 0.90)
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.
