1. Visual Perception and Understanding
Object detection and tracking in complex environments
Joint semantic segmentation and scene parsing
Temporal modeling for behavior recognition and analysis
2. 3D Vision and Spatial Reconstruction
Monocular/stereo depth estimation and matching
Point cloud processing, surface reconstruction, and mesh generation
Simultaneous localization and mapping (SLAM) for robotics and AR
3. Generative and Synthetic Vision Models
Advances in GAN-based image synthesis
Style transfer, domain adaptation, and cross-domain visual generation
High-fidelity image and video content generation
4. Vision-Oriented Communication Technologies
Efficient visual data transmission under low bandwidth
Intelligent coding and streaming for real-time video
Compression algorithms with feature preservation for vision tasks
5. Human-AI Interaction and Interface Design
Multimodal interfaces for human-machine communication
Vision-based gesture recognition and affective computing
Integrated systems combining speech, vision, and motion
6. Intelligent Algorithm Development and Optimization
Transformer and graph-based approaches for vision tasks
Efficient training and optimization of large-scale models
Adaptive and self-evolving algorithmic frameworks
7. Scalable Computing Architectures
Distributed and parallel computing for vision workloads
Edge–cloud collaborative architectures
Model compression, acceleration, and lightweight deployment
8. Optics and Imaging for Vision Systems
Computational imaging and Fourier optics
Lens design, camera architectures, and optical neural networks
Light-field sensing, hyperspectral imaging, and optical metrology for vision