Research map / Vision-language and multimodal / CLIP and zero-shot
Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection
Ting Lei, Shaofeng Yin, Yuxin Peng, Yang Liu
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 conditional language prompts (ablation) | CMMP · HICO-DET UV | mAP unseen: 19.40 -> 26.23 | Improved |
| add conditional vision prompts (ablation) | CMMP · HICO-DET UV | mAP seen: 26.03 -> 32.75 | Improved |
| add instance-level prior to vision prompts (ablation) | CMMP · HICO-DET UV | mAP unseen: 25.07 -> 26.23 | Improved |
| add global spatial pattern prior (ablation) | CMMP · HICO-DET UV | mAP unseen: 24.92 -> 26.23 | Improved |
| add consistency loss (lambda_cc 0 -> 1.0) (ablation) | CMMP language prompts · HICO-DET UV | mAP unseen: 24.49 -> 26.23 | Improved |
| increase consistency loss weight from 1.0 to 2.0 (ablation) | CMMP language prompts · HICO-DET UV | mAP unseen: 26.23 -> 24.45 | Hurt |
| scale CMMP backbone from ViT-B/16 to ViT-L/14 | CMMP · HICO-DET UC | mAP unseen: 29.60 -> 34.46 | Improved |
| use CMMP instead of CLIP4HOI under RF-UC | zero-shot HOI detector · HICO-DET RF-UC | mAP seen: 35.48 -> 32.87 | Hurt |
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.
- HOICLIP — HOICLIP: Efficient Knowledge Transfer for HOI Detection With Vision-Language Models (CVPR 2023) · 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
- Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection (NeurIPS 2025 · similarity 0.93)
- Open-World Human-Object Interaction Detection via Multi-modal Prompts (CVPR 2024 · similarity 0.93)
- EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection (NeurIPS 2024 · similarity 0.92)
- Locality-Aware Zero-Shot Human-Object Interaction Detection (CVPR 2025 · similarity 0.91)
- Orchestrating the Symphony of Prompt Distribution 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 0.90)
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.
