AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection

Yupeng Hu, Changxing Ding, Chang Sun, Shaoli Huang, Xiangmin Xu

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
add attention bias guidance (ABG) from the HOI detector to the VLM (ablation)BC-HOI with early fusion · HICO-DET closed (Default)mAP (Full): 39.34 -> 42.60Improved
add LLM-based supervision guidance (LSG) (ablation)BC-HOI with early fusion · HICO-DET closed (Default)mAP (Full): 39.34 -> 42.41Improved
add early fusion of CNN and BLIP-2 feature maps (ablation)late-fusion baseline · HICO-DET closed (Default)mAP (Full): 38.91 -> 39.34Improved
replace detector-provided adaptive attention bias with plain learnable bias (ablation)BC-HOI · HICO-DET NF-UCmAP (Full): 36.40 -> 32.60Hurt
use token-level LLM supervision rather than caption-level holistic supervision (ablation)LSG · HICO-DET NF-UCmAP (Full): 35.56 -> 36.40Improved
take attention bias from both detection and interaction decoders (averaged) instead of interaction decoder only (ablation)ABG · HICO-DET NF-UCmAP (Full): 36.40 -> 35.62Hurt
apply attention bias to both ViT encoder and Q-Former (ablation)ABG · HICO-DET NF-UCmAP (Full): 35.45 (ViT only) -> 36.40Improved
predict all caption tokens with larger weights on nouns and verbs (ablation)LSG · HICO-DET NF-UCmAP (Full): 35.74 (nouns and verbs only) -> 36.14 (equal weights) -> 36.40Improved
use QwenVL-7B instead of GPT-4o for captions (ablation)LSG · HICO-DET NF-UCmAP (Full): 36.40 -> 36.24No clear effect
BC-HOI versus UniHOI on UO unseen categoriesBC-HOI · HICO-DET UOmAP (Unseen): 19.72 -> 19.94No clear effect
add VLM interaction via ABG/LSG versus UniHOIBC-HOI · Inference costtime per image: 82.3ms -> 99.7msHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy