18 citations · 35 across the 15 of their papers we have counts for
16 papers
WSA: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control
Jiahao Jiang, Jianing Zhang, Zhenhan Yin +9
World-Action Models (WAMs) have emerged as a promising paradigm for robot control by using predicted world evolution to guide action generation. However, existing WAMs largely foll…
MiVLA: Towards Generalizable Vision-Language-Action Model with Human-Robot Mutual Imitation Pre-training
Zhenhan Yin, Xuanhan Wang, Jiahao Jiang +8
While leveraging abundant human videos and simulated robot data poses a scalable solution to the scarcity of real-world robot data, the generalization capability of existing vision…
Pseudo-Label Refinement for Robust Wheat Head Segmentation via Two-Stage Hybrid Training
Jiahao Jiang, Zhangrui Yang, Xuanhan Wang +1
This extended abstract details our solution for the Global Wheat Full Semantic Segmentation Competition. We developed a systematic self-training framework. This framework combines…
Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models
Xuanhan Wang, Huimin Deng, Ke Liu +3
Human-centric vision models (HVMs) have achieved remarkable generalization due to large-scale pretraining on massive person images. However, their dependence on large neural archit…
Learning Generalizable and Efficient Image Watermarking via Hierarchical Two-Stage Optimization
Ke Liu, Xuanhan Wang, Qilong Zhang +2
Deep image watermarking, which refers to enabling imperceptible watermark embedding and reliable extraction in cover images, has been shown to be effective for copyright protection…
Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models
Xuanhan Wang, Huimin Deng, Lianli Gao +1
Human-centric visual perception (HVP) has recently achieved remarkable progress due to advancements in large-scale self-supervised pretraining (SSP). However, existing HVP models f…
Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection
Youheng Sun, Shengming Yuan, Xuanhan Wang +2
Targeted adversarial attack, which aims to mislead a model to recognize any image as a target object by imperceptible perturbations, has become a mainstream tool for vulnerability…
X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attention
Yixuan Zhou, Xuanhan Wang, Xing Xu +2
High-resolution representation is necessary for human pose estimation to achieve high performance, and the ensuing problem is high computational complexity. In particular, predomin…
CIParsing: Unifying Causality Properties into Multiple Human Parsing
Xiaojia Chen, Xuanhan Wang, Lianli Gao +3
Existing methods of multiple human parsing (MHP) apply statistical models to acquire underlying associations between images and labeled body parts. However, acquired associations o…
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…
Technical Report: Disentangled Action Parsing Networks for Accurate Part-level Action Parsing
Xuanhan Wang, Xiaojia Chen, Lianli Gao +2
Part-level Action Parsing aims at part state parsing for boosting action recognition in videos. Despite of dramatic progresses in the area of video classification research, a sever…
From General to Specific: Informative Scene Graph Generation via Balance Adjustment
Yuyu Guo, Lianli Gao, Xuanhan Wang +5
The scene graph generation (SGG) task aims to detect visual relationship triplets, i.e., subject, predicate, object, in an image, providing a structural vision layout for scene und…