Important: Please note that the policies have been extensively updated from previous years, including guidelines related to code submission, research areas, and code of conduct.

Papers in the main technical program must describe high-quality, original research. Topics of interest include the following aspects of computer vision and pattern recognition (in alphabetical order):

    3D from a single image and shape-from-x
    3D shape modeling and processing
    Action and behavior recognition
    Adversarial learning
    Biometrics
    Body gestures and pose
    Computational photography
    Datasets and evaluation
    Detection and localization in 2D and/or 3D
    Efficient training and inference methods
    Explainable AI for CV
    Faces
    Fairness, accountability, transparency, and ethics in vision
    First person (Egocentric) vision
    Image and video manipulation detection
    Image and video retrieval
    Image and video synthesis
    Low-level and physics-based vision
    Low-shot learning
    Machine learning architectures and formulations
    Medical, biological, and cell microscopy
    Motion and tracking
    Neural generative models
    Optimization and learning methods
    Recognition and classification
    Representation learning
    Scene analysis and understanding
    Scene text and document understanding
    Segmentation, grouping, and shape
    Semi / Weak / Self / Unsupervised lLearning
    Stereo, 3D from multiview and other sensors
    Transfer learning
    Video analysis and understanding
    Vision + language
    Vision + other modalities
    Vision applications and systems
    Vision for and autonomous vehicles
    Vision for robotics and embodied vision
    Visual reasoning and logical representation

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.