(The following topics include but are not limited to)
Track 1: Computer Vision
Image/Video Processing (Enhancement, Segmentation, Object Detection and Tracking)
3D Computer Vision and Point Cloud Processing
Multimodal Visual Perception and Cross-modal Semantic Alignment
Visual Foundation Models, Visual Language Models (VLM) and Visual Object Models (VOM)
Generative Visual Content (AIGC) and Diffusion Models
Remote Sensing Image Analysis and Interpretation
Face Recognition, Biometric Recognition and Behavior Analysis
Visual Feature Extraction, Representation Learning and Self/Semi/Autonomous Learning
Video Understanding (Action Recognition, Event Analysis)
Computational Photography, Image Generation and Style Transfer
Lightweight Design of Visual Models and Edge Deployment
Interpretability, Robustness and Privacy Protection of Visual Models and Large Visual Models
Integration of Vision and Language/Reasoning
Visual Perception in Autonomous Driving
Track 2: Embodied Intelligence and Robot Systems
Learning, Adaptation and Generalization in Embodied Systems
Multimodal Perception and Interaction in Embodied Intelligence
Construction of World Models for Embodied Agents
Small Sample Learning, Continuous/Lifelong Learning for Embodied Agents
Reinforcement Learning and Cognitive Reasoning for Embodied Systems
Integration, Deployment and Edge Computing of Embodied Robot Systems
Path Planning, Decision Making and Motion Control for Embodied Agents
Human-Human Embodied Interaction and Collaboration
Design and Optimization of Embodied Systems
Scale Laws and Emergent Capabilities in Embodied Systems
Migration from Simulation to Reality, Digital Twinning and Robot Simulation
Multimodal Sensing (Tactile, Force Sensing, Lidar, etc.) and Sensor Fusion
Embodied Cognitive Computing, Sensing-Motion Representation and Adaptive Perception Strategies
...