
On July 25, 2026, the Chinese Association for Artificial Intelligence (CAAI) Pattern Recognition Expert Forum on "Multimodal Visual Perception and Generation"-organized by the CAAI and hosted by the CAAI Pattern Recognition Technical Committee-will be held at Wuhan University.With the rapid development of cutting-edge technologies such as multimodal systems, large models, and embodied intelligence, computer vision is entering a new era of promising opportunities.
With the theme "Multimodal Visual Perception and Generation," this expert forum will feature invited presentations by experts and scholars in the fields of visual computing, embodied intelligence, robot learning, and intelligent perception, focusing on topics such as the semantic representation of visual signals, human-like visual perception, multimodal perception in embodied intelligence, and autonomous decision-making.The forum will focus on key challenges in multimodal visual perception and generation within complex real-world scenarios. It will explore how visual perception supports intelligent agents in understanding the physical world, how to transition from human-like visual perception to embodied intelligence in robots, how to enhance multimodal perception and autonomous decision-making capabilities, as well as the development trends and application prospects of cutting-edge technologies such as hybrid AI architectures.
We cordially invite faculty, students, researchers, and industry representatives from relevant fields to attend and exchange ideas, and to jointly explore innovative developments in multimodal visual perception and generation technologies in the areas of visual computing and embodied intelligence.Professor Wang Mi, Wuhan University, Deputy Director of the State Key Laboratory of Geomatics and Remote Sensing Information EngineeringProfessor Du Bo, Wuhan University, Director of the Office of Development Planning and Discipline Construction