5 papers
QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection
Yuxiao Wang, Wolin Liang, Yu Lei +3
Human-Object Interaction (HOI) detection aims to localize human-object pairs and recognize their interactions in images. Although DETR-based methods have recently emerged as the ma…
What-Meets-Where: Unified Learning of Action and Contact Localization in Images
Yuxiao Wang, Yu Lei, Wolin Liang +4
People control their bodies to establish contact with the environment. To comprehensively understand actions across diverse visual contexts, it is essential to simultaneously consi…
Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss
Yuxiao Wang, Yu Lei, Zhenao Wei +4
The task of Human-Object conTact (HOT) detection involves identifying the specific areas of the human body that are touching objects. Nevertheless, current models are restricted to…
OpenVidVRD: Open-Vocabulary Video Visual Relation Detection via Prompt-Driven Semantic Space Alignment
Qi Liu, Weiying Xue, Yuxiao Wang +1
The video visual relation detection (VidVRD) task is to identify objects and their relationships in videos, which is challenging due to the dynamic content, high annotation costs,…
Precision-Enhanced Human-Object Contact Detection via Depth-Aware Perspective Interaction and Object Texture Restoration
Yuxiao Wang, Wenpeng Neng, Zhenao Wei +6
Human-object contact (HOT) is designed to accurately identify the areas where humans and objects come into contact. Current methods frequently fail to account for scenarios where o…