3 papers
cs.CV2026
OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation
Yiren Song, Xiyao Deng, Pei Yang +2
Cross-embodiment video generation aims to transfer motions across different humanoid embodiments, such as human-to-robot and robot-to-robot, enabling scalable data generation for e…
cs.CV2022
Modeling Hierarchical Structural Distance for Unsupervised Domain Adaptation
Yingxue Xu, Guihua Wen, Yang Hu +1
Unsupervised domain adaptation (UDA) aims to estimate a transferable model for unlabeled target domains by exploiting labeled source data. Optimal Transport (OT) based methods have…
cs.CV2020
Graph-based Visual-Semantic Entanglement Network for Zero-shot Image Recognition
Yang Hu, Guihua Wen, Adriane Chapman +5
Zero-shot learning uses semantic attributes to connect the search space of unseen objects. In recent years, although the deep convolutional network brings powerful visual modeling…