Workshop Agenda
*Subject to Change
9:00-9:10 AM | Opening Welcome Remarks by NYU Shanghai Dean Nasir Memon
Keynote Talks
9:10-10:00 AM | Prof. Qionghai Dai, Academician of the Chinese Academy of Engineering, Tsinghua University, “Meta-imaging: From Microscopic Imaging to Astronomical Observation (元成像：从显微成像到天文观测)” (Prof. Dai’s Chinese talk abstract and bio can be found here).
10:00-10:50 AM | Prof. Wenwu Zhu, Tsinghua University, “Disentangled Visual Generation in Dynamic Open Environment”
10:50-11:05 AM | Coffee/Tea Break
Session 1: Generative Visual Signal Processing
11:05-11:20 AM | Prof. Hongkai Xiong, Shanghai Jiao Tong University, “Thinking with video, object level representation, reasoning, scheduling and generation”
11:20-11:35 AM | Prof. Bing Zeng, UESTC, YOHO, "Single-image-based deep learning for accurate segmentation of early esophageal cancer lesions"
11:35-11:50 AM | Prof. Zhibo Chen, USTC, “Integrating Low-Level Image Processing with Generative AI and Intelligent Agents”
11:50-12:05 AM | Prof. Zhihai He, Southern University of Science and Technology, “Generative and Agentic Methods for Visual Signal Processing”
12:05-1:00 PM | Lunch (on campus)
Session 2: Computational Imaging and Visual Signal Processing
1:00-1:15 PM | Prof. Xun Cao, Nanjing University, “AI-empowered computational imaging: Beyond the frontiers of vision and cognition”
1:15-1:30 PM | Prof. Jingyu Yang, Tianjin University, “Physics-informed learning for high-resolution light-field”
1:30-1:45 PM | Prof. Yebin Liu, Tsinghua University, “Fusion of Reconstruction and Generation for 3D/4D Reconstruction”
1:45-2:00 PM | Prof. Kun Li, Tianjin University, “Crowd reconstruction and generation in a large scene”
2:00-2:15 PM | Prof. Jiaying Liu, Peking University, “Toward general image enhancement: from data fitting to relation modeling”
2:15-2:30 PM | Prof. Xinggang Wang, Huazhong University of Science and Technology, “High efficiency representation learning for visual understanding and visual generation and vision-action models”
2:30-2:45 PM | Prof. Yuxing Han, Tsinghua Shenzhen International Graduate School, “Vision-enabled precision agricultural aviation: a 10-year retrospective”
2:45-3:00 PM | Coffee/Tea Break
Session 3: AI for Visual Signal Compression
3:00-3:15 PM | Prof. Lu Yu, Zhejiang University, “Representation and compression of spatial visual signal”
3:15-3:30 PM | Prof. Zhan Ma, Nanjing University, “Visual coding for intelligence”
3:30-3:45 PM | Prof. Jie Liang, Eastern Institute of Technology, “Application of wavelet transform in learned image compression”
3:45-4:00 PM | Prof. Yun Zhang, Sun Yat-Sen University, “Deep Learning based Perceptual Modeling and Video Coding for Machines”
4:00-4:15 PM | Prof. Ping An, Shanghai University, “Efficient light field data representation and reconstruction based on view sparsity”
4:15-4:30 PM | Prof. Li Song, Shanghai Jiao Tong University, “AI-driven Multimodal Data Compression”
4:30-4:45 PM | Coffee/Tea Break
4:45-5:45 PM | Panel Discussion: Future of AI for Visual Signal Processing
Moderator:
- Jiangtao (Gene) Wen, NYU Shanghai
Panelists:
- Xun Cao, Nanjing University
- Zhibo Chen, University of Science and Technology of China
- Jiaying Liu, Peking University
- Zhan Ma, Nanjing University
- Hongkai Xiong, Shanghai Jiao Tong University
- Yun Zhang, Sun Yat-Sen University
6:30-8:30 PM | Dinner (E903-904)
Location
New Bund Campus, NYU Shanghai
567 West Yangsi Road, Pudong New District, Shanghai, China 200124
Metro: Oriental Sports Center Station, Metro Lines 6/8/11 (Exit 3)
Bus: Bus Lines 82/314/583/973/810/986/873
