18 citations · 35 across the 15 of their papers we have counts for
5 papers · 1 filter
RepParser: End-to-End Multiple Human Parsing with Representative Parts
Xiaojia Chen, Xuanhan Wang, Lianli Gao +1
Existing methods of multiple human parsing usually adopt a two-stage strategy (typically top-down and bottom-up), which suffers from either strong dependence on prior detection or…
Skeleton-based Action Recognition via Adaptive Cross-Form Learning
Xuanhan Wang, Yan Dai, Lianli Gao +1
Skeleton-based action recognition aims to project skeleton sequences to action categories, where skeleton sequences are derived from multiple forms of pre-detected points. Compared…
KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing
Xuanhan Wang, Jingkuan Song, Xiaojia Chen +3
Part-level attribute parsing is a fundamental but challenging task, which requires the region-level visual understanding to provide explainable details of body parts. Most existing…
KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences
Xuanhan Wang, Lianli Gao, Yixuan Zhou +2
Human densepose estimation, aiming at establishing dense correspondences between 2D pixels of human body and 3D human body template, is a key technique in enabling machines to have…
Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation
Qilong Zhang, Youheng Sun, Chaoning Zhang +4
In recent years, the adversarial vulnerability of deep neural networks (DNNs) has raised increasing attention. Among all the threat models, no-box attacks are the most practical bu…