Research map / Detection and segmentation / Open-set and few-shot detection
Learning to Detect Human-Object Interactions With Knowledge
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 |
|---|---|---|---|
| use knowledge graph and multimodal joint embeddings | HOI detection with ResNet-50 · HICO-DET, Rare | role mAP (%): 10.21 -> 13.26 | Helped |
| use knowledge graph and multimodal joint embeddings | HOI detection with ResNet-50 · HICO-DET, Full | role mAP (%): 13.11 -> 14.70 | Helped |
| use knowledge graph and multimodal joint embeddings | HOI detection with ResNet-50 · V-COCO, Scenario 1 | role mAP (%): 45.3 -> 45.9 | Helped |
| add extra knowledge (ablation) | HOI detection · V-COCO, Scenario 1 | role mAP (%): 42.4 -> 45.9 | Helped |
| add extra knowledge (ablation) | HOI detection · HICO-DET, Rare | role mAP (%): 10.21 -> 13.26 | Helped |
| use multimodal joint embedding rather than concatenated vectors (ablation) | HOI detection · HICO-DET, Rare | role mAP (%): 11.59 -> 13.26 | Helped |
| use graph convolution to model semantic dependencies (ablation) | HOI detection · HICO-DET, Rare | role mAP (%): 11.63 -> 13.26 | Helped |
| include external visual-relationships annotations in the knowledge graph (ablation) | HOI detection · HICO-DET, Full | role mAP (%): 13.91 -> 14.70 | Helped |
| include external visual-relationships annotations in the knowledge graph (ablation) | HOI detection · V-COCO, Scenario 1 | role mAP (%): 45.1 -> 45.9 | Helped |
Closest papers by meaning
- LINK: Learning Instance-level Knowledge from Vision-Language Models for Human-Object Interaction Detection (ICLR 2026 · similarity 0.92)
- Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning (ICLR 2023 · similarity 0.92)
- Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection (CVPR 2024 · similarity 0.91)
- Exploring Pose-Aware Human-Object Interaction via Hybrid Learning (CVPR 2024 · similarity 0.91)
- Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models (NeurIPS 2024 · similarity 0.90)
- Open-World Human-Object Interaction Detection via Multi-modal Prompts (CVPR 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.