Including but not limited to the following contents:
Track 1: Computer Vision
Image classification and object detection
Semantic segmentation and instance segmentation
Video understanding and behavior recognition
Multimodal representation learning
Self-supervised and semi-supervised learning
Few-shot and zero-shot learning
Interpretable computer vision
Vision-based models and fine-tuning
Adversarial attacks and defenses
Visual language models and cross-modal reasoning
Track 2: 3D Imaging Technology
3D reconstruction and multi-view geometry
Structured light and TOF imaging
Motion recovery structure and SLAM
Neural radiance fields and neural rendering
3D point cloud processing and understanding
Depth estimation and stereo vision
Computational imaging and computational photography
Multispectral and hyperspectral imaging
Gaussian sputtering and differentiable rendering
3D generative models and shape completion
Track 3: Cross-Applications
Visual SLAM and autonomous navigation
Robot vision and perception
Autonomous driving vision perception
Medical imaging and biomedical imaging
Remote sensing and photoelectric imaging
Edge computing and lightweight visual deployment
Industrial visual inspection
Augmented reality and mixed reality
Embodied intelligence and active perception
Visual-language navigation and operation