Huayu Wang — accepted AI-conference papers

2026

CLEP: Contrastive Language-Pose Pretraining

Sen Jia, Huayu Wang, Hsiang-Wei Huang, Zhaochong An, Jenq-Neng Hwang, Huaping Zhang +1

CVPR 2026

Aligning natural language descriptions with precise 3D human poses remains a big challenge due to the scarcity of effective pose representation mechanisms and large-scale, semantically rich datasets. To overcome these limitations, we first introduce **CLEP-2M**, the largest 3D pose-language dataset

Cited by 0 Source ↗Scholar ↗

2024

Domain-Adaptive Semantic Segmentation Emerges From Vision-Language Supervised Domain-Debiased Self-Training

Huayu Wang, Zekun Jiang, Lingxi Xie, Dongsheng Jiang, Wei Shen, Qi Tian

ICASSP 2024accepted

Unsupervised domain adaptive semantic segmentation leverages synthetic data to train a segmentation model and transfers it to unlabeled real images. Due to the style difference, the transferred model suffers from the domain gap. Even worse, some classes exhibit the extreme domain gap, where the feat…

Cited by 0 Source ↗Scholar ↗