Imaging, Processing, Perception, and Reasoning for High-Dimensional Visual Data
Imaging, Processing, Perception, and Reasoning for High-Dimensional Visual Data
Title
Imaging, Processing, Perception, and Reasoning for High-Dimensional Visual Data
Description
Recent advances in sensors, computational optics, and neural modeling have enabled a new generation of highdimensional visual data. These data types capture much richer information about scenes in terms of space, time, angle, spectrum, and modality. Event cameras enable ultra-fast motion capture with high dynamic range. Neural radiance fields model full 3D scenes from sparse views. Multi-modal fusion of LiDAR, thermal, and RGB data supports autonomous systems. However, processing and interpreting such data remains a major challenge due to the curse of dimensionality, the lack of large-scale benchmarks, and limited understanding of cross-domain generalization.
Our workshop aims to explore these challenges in depth. We invite contributions on efficient data representations, learning-based reconstruction methods, cross-modality alignment techniques, and semantics-aware reasoning frameworks for high-dimensional multimedia data. These topics are essential not only for advancing multimedia understanding, but also for enabling practical applications in areas such as autonomous driving, robotics, medical imaging, augmented and virtual reality, and remote sensing.
Workshop Website
Organizers
• Zeyu Xiao, National University of Singapore
• Zhuoyuan Li, University of Science and Technology of China (USTC), Hefei, China
• Xiang Chen, Nanjing University of Science and Technology, China
• Cong Zhang, The Chinese University of Hong Kong
• Hadi Amirpour, University of Klagenfurt, Austria
• Yakun Ju, University of Leicester
• Zhiwei Xiong, University of Science and Technology of China (USTC)
• Kin-Man Lam, The Hong Kong Polytechnic University
Contact Person
• Zeyu Xiao (zeyuxiao@nus.edu.sg)
© 2025 ACM Multimedia Asia Conference. All Rights Reserved.