Publications

Zhenghao Zhang, Junchao Liao, Menghao Li, Long Qin, Weizhi Wang (2024). Tora: Trajectory-oriented Diffusion Transformer for Video Generation. arXiv.

Hao Wang, Junchao Liao, Tianheng Cheng, Zewen Gao, Hao Liu, Bo Ren, Xiang Bai, Wenyu Liu (2022). Knowledge Mining with Scene Text for Fine-Grained Recognition. CVPR.