CVPR 2021 : Conference on Computer Vision and Pattern Recognition

Papers in the main technical program must describe high-quality, original research. Topics of interest include all aspects of computer vision and pattern recognition including, but not limited to:

• 2D object recognition
• 3D computer vision   
• 3D object recognition
• Action and behavior recognition   
• Adversarial learning, adversarial attack and defense methods
• Biometrics, face, gesture, body pose
• Computational photography
• Datasets and evaluation   
• Efficient training and inference methods for networks   
• Explainable AI, fairness, accountability, privacy, transparency and ethics in vision   
• Image and video retrieval   
• Image and video synthesis
• Image classification
• Low-level and physics-based vision   
• Machine learning architectures and formulations   
• Medical, biological and cell microscopy   
• Motion and tracking   
• Optimization and learning methods   
• Pose estimation
• Representation learning, deep learning   
• Scene analysis and understanding   
• Transfer, low-shot, semi- and un- supervised learning   
• Video analysis and understanding   
• Vision + language, vision + other modalities   
• Vision applications and systems, vision for robotics and autonomous vehicles

All submissions will be handled electronically. In addition to the main technical program, the conference will include Tutorials, Workshops, Demonstrations, and Exhibits. Submit proposals to the appropriate chair.