I’m a second-year Ph.D. student in the School of Computer Science at Fudan University, supervised by Prof. Zuxuan Wu and Prof. Yu-Gang Jiang.

My research interests lie in computer vision and deep learning, with an emphasis on video understanding and generation, e.g., crowd counting, video-language retrieval, general video generation, and customized video generation.

Publication

• MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing. Haoyu Zhao, Tianyi Lu, Jiaxi Gu, Xing Zhang, Qingping Zheng, Zuxuan Wu, Hang Xu, Yu-Gang Jiang. ECCV 2024.
• SPACE: Finding key-speaker in complex multi-person scenes. Haoyu Zhao, Weidong Min, Jianqiang Xu, Qing Han, Wei Li, Qi Wang, Ziyuan Yang, Linghua Zhou. IEEE Transactions on Emerging Topics in Computing (TETC).
• Need Only One More Point (NOOMP): Perspective Adaptation Crowd Counting in Complex Scenes. Haoyu Zhao, Qi Wang, Guowei Zhan, Weidong Min, Yi Zou, Shimiao Cui. IEEE Transactions on Multimedia (TMM).
• Scene-adaptive crowd counting method based on meta learning with dual-input network DMNet. Haoyu Zhao, Weidong Min, Jianqiang Xu, Qi Wang, Yi Zou, Qiyan Fu. Frontiers of Computer Science (FCS).
• MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting. Haoyu Zhao, Weidong Min, Xin Wei, Qi Wang, Qiyan Fu, Zitai Wei. IET Image Processing (IET IP).
• Memory-efficient document layout analysis method using LD-net. Haoyu Zhao, Weidong Min, Qi Wang, Zitai Wei. Multimedia Tools and Applications.
• Illumination-Enhanced Crowd Counting Based on IC-Net in Low Lighting Conditions. Haoyu Zhao, Weidong Min, Yi Zou. International Conference on Image and Graphics (ICIG).
• Reuse and diffuse: Iterative denoising for text-to-video generation. Jiaxi Gu, Shicong Wang, Haoyu Zhao, Tianyi Lu, Xing Zhang, Zuxuan Wu, Songcen Xu, Wei Zhang, Yu-Gang Jiang, Hang Xu. arXiv preprint arXiv:2309.03549.
• Inter-domain adaptation label for data augmentation in vehicle re-identification. Qi Wang, Weidong Min, Qing Han, Qian Liu, Cheng Zha, Haoyu Zhao, Zitai Wei. IEEE Transactions on Multimedia (TMM).
• Dual similarity pre-training and domain difference encouragement learning for vehicle re-identification in the wild. Qi Wang, Yuling Zhong, Weidong Min, Haoyu Zhao, Di Gai, Qing Han. Pattern Recognition.

Academic Services

Conference Reviewer for ACM MM 2024.

Journal Reviewer for TIP, NCAA etal.

Awards

National Scholarship (Top1%). 2021.

Updated at 16. Jul. 2024.