Including but not limited to the following contents:
Track 1: Robot Vision
Vision sensors and calibration
Stereo vision and depth estimation
Visual SLAM and positioning
Object detection and semantic segmentation
Visual servoing and target tracking
3D point cloud processing and recognition
Optical flow and motion estimation
Multi-view geometry and 3D reconstruction
Visual-inertial fusion navigation
Instance segmentation and panoramic segmentation
Visual anomaly detection
Event cameras and dynamic vision
Visual attention mechanism

Lightweight visual models and embedded deployment

Track 2： Machine Learning
Supervised learning and classification/regression
Unsupervised learning and clustering dimensionality reduction
Semi-supervised and self-supervised learning
Deep learning network architectures
Reinforcement learning and sequential decision-making
Transfer learning and domain adaptation
Meta-learning and small sample learning
Generative models
Graph neural networks
Federated learning and privacy protection
Interpretable machine learning
Adversarial learning and robustness
Multi-task learning
Multimodal learning and cross-modal alignment

Large model fine-tuning and prompt learning

Track 3： Object Recognition
Image object detection and localization
Object tracking and re-identification
3D object recognition and pose estimation
Infrared/Radar/Multi-modal object recognition
Small object detection and recognition
Object feature extraction and representation
Template matching and correlation filtering
Deep feature learning
Zero-shot and out-of-distribution recognition
Attention mechanism in object recognition
Object recognition datasets and benchmarks
Real-time object recognition and edge deployment
Joint detection-tracking-recognition framework