Dai, Pengwen

5 publications

CVPR 2025 CLIP Is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval Without OCR Xugong Qin, Peng Zhang, Jun Jie Ou Yang, Gangyan Zeng, Yubo Li, Yuanyuan Wang, Wanqian Zhang, Pengwen Dai

ICLR 2025 Decoupled Graph Energy-Based Model for Node Out-of-Distribution Detection on Heterophilic Graphs Yuhan Chen, Yihong Luo, Yifan Song, Pengwen Dai, Jing Tang, Xiaochun Cao

IJCAI 2025 Endogenous Recovery via Within-Modality Prototypes for Incomplete Multimodal Hashing Sa Zhu, Dayan Wu, Chenming Wu, Pengwen Dai, Bo Li

NeurIPS 2025 Towards Irreversible Attack: Fooling Scene Text Recognition via Multi-Population Coevolution Search Jingyu Li, Pengwen Dai, Mingqing Zhu, Chengwei Wang, Haolong Liu, Xiaochun Cao

CVPR 2021 Progressive Contour Regression for Arbitrary-Shape Scene Text Detection Pengwen Dai, Sanyi Zhang, Hua Zhang, Xiaochun Cao