SCOPE

The International Conference on Computer Vision Theory and Applications aims at becoming a major point of contact between researchers, engineers and practitioners on the area of computer vision methodology and systems, and their application. Five simultaneous tracks will be held, covering all different aspects related to computer vision: Foundations & Representation Learning; Recognition & Detection; Low-level Vision & Computational Imaging; and 3D Vision, Motion, Robotics, Application & Systems. We welcome papers describing original work in any of the areas listed below. Papers describing advanced prototypes, systems, tools and techniques as well as general survey papers indicating future directions are also encouraged. Paper acceptance will be based on quality, relevance to the conference themes and originality. The conference program will include both oral and poster presentations. Special sessions, dedicated to case-studies and commercial presentations, as well as technical tutorials, dedicated to technical/scientific topics, are also envisaged.

CONFERENCE AREAS

The last decade has seen a revolution in the theory and application of Artificial Intelligence and Machine Learning in Computer Vision. In this conference edition, we look at advanced in Computer Vision based on Machine Learning methods. Each of these topic areas is expanded below but the sub-topics list is not exhaustive. Papers may address one or more of the listed sub-topics, although authors should not feel limited by them. Unlisted but related sub-topics are also acceptable, provided they fit in one of the following main topic areas:

1. FOUNDATIONS & REPRESENTATION LEARNING
2. RECOGNITION & DETECTION
3. LOW-LEVEL VISION & COMPUTATIONAL IMAGING
4. 3D VISION, MOTION, ROBOTICS, APPLICATION & SYSTEMS

AREA 1: FOUNDATIONS & REPRESENTATION LEARNING

Deep Learning for Visual Understanding
Domain Adaptation
Generative AI
Machine Learning Technologies for Vision
Multi-task learning
Self-supervised Learning
Transfer Learning

AREA 2: RECOGNITION & DETECTION

Categorization and Scene Understanding
Event and Human Activity Recognition
Face and Expression Recognition
Few-Shot Learning
Object and Face Recognition
Object Detection and Localization
Segmentation and Grouping

AREA 3: LOW-LEVEL VISION & COMPUTATIONAL IMAGING

Color and Texture Analyses
Features Extraction
Image Enhancement and Restoration
Image Formation, Acquisition Devices and Sensors
Image Registration
Multimodal and Multi-Sensor Models of Image Formation
Shape Representation and Matching
Visual Attention and Image Saliency

AREA 4: 3D VISION, MOTION, ROBOTICS, APPLICATION & SYSTEMS

3D Deep Learning
Assistive Computer Vision
Content-Based Indexing, Search, and Retrieval
Deep Learning for Tracking
Device Calibration, Characterization and Modeling
Egocentric Vision for Interaction Understanding
Entertainment Imaging Applications
Human and Computer Interaction
Image-Based Modeling and 3D Reconstruction
Imaging and Vision for Cultural Heritage
Medical Image Applications
Mobile and Egocentric Localization
Mobile and Egocentric Object Detection and Recognition
Mobile Vision
Multimedia Forensics
Optical Flow and Motion Analyses
Simultaneous Localization and Mapping
Stereo Vision and Structure from Motion
Tracking and Visual Navigation
Video Surveillance and Event Detection
Vision for Robotics