长期招收本科生和研究生。本实验室专注探索多模态理解中的各类前沿问题,组内风格自由平等、简单高效,GPU充足,能提供充分、有效的科研指导。欢迎对学术有兴趣有想法、敢于探索尝试,或有较强代码能力的同学与我交流联系。
24年已无名额。如果的确对我的实验室感兴趣,请尽早联系,越早越好,我的名额非常非常有限。
Exploring Intrinsic Dimension for Vision-Language Model Pruning.
Hanzhang Wang, Jiawen Zhang, and Qingyuan Ma
Forty-first International Conference on Machine Learning (ICML). 2024.
Evolutionary Recurrent Neural Network for Image Captioning.
Hanzhang Wang, Hanli Wang, and Kaisheng Xu
Neurocomputing. 2020: 401, 249-256. (SCI)
Swell-and-Shrink: Decomposing Image Captioning by Transformation and Summarization.
Hanzhang Wang, Hanli Wang, and Kaisheng Xu
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI). 2019: 5226-5232. (CCF-A)
Categorizing concepts with basic level for vision-to-language.
Hanzhang Wang, Hanli Wang, and Kaisheng Xu
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018: 4962-4970. (CCF-A)
Richer semantic visual and language representation for video captioning.
Pengjie Tang, Hanli Wang, Hanzhang Wang, and Kaisheng Xu
Proceedings of the 25th ACM international conference on Multimedia (ACM MM). 2017: 1871-1876. (CCF-A)
Powered by Jekyll and Minimal Light theme.