16th International Conference on Computer Vision Theory and Applications - VISAPP 2021 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 application systems. Five simultaneous tracks will be held, covering all different aspects related to computer vision: Image Formation and Preprocessing; Image and Video Analysis and Understanding; Motion, Tracking and Stereo Vision; and Applications and Services. Fundamental Research 8 February 2021 - 10 February 2021 Vienna, Austria © INSTICC 16th International Conference on Computer Vision Theory and Applications VISAPP Website: http://www.visapp.visigrapp.org February 8 - 10, 2021 Vienna, Austria In Cooperation with: EUROGRAPHICSProceedings will be submitted for indexation by: SCOPUS, Google Scholar, DBLP, Semantic Scholar, Microsoft Academic, EI and Conference Proceedings Citation Index. IMPORTANT DATES: Regular Paper Submission: September 14, 2020 Authors Notification (regular papers): November 12, 2020 Final Regular Paper Submission and Registration: November 26, 2020 Conference Topics:Area 1: Applications and Services- Entertainment Imaging Applications- Media Watermarking and Security- Multimedia Forensics- Assistive Computer Vision- Mobile Imaging- Imaging and Vision for Cultural Heritage- Camera Networks and Vision- Document Imaging in Business- Medical Image Applications- Human and Computer Interaction- Digital PhotographyArea 2: Image and Video Formation, Preprocessing and Analysis- Image Formation, Acquisition Devices and Sensors- Device Calibration, Characterization and Modeling- Image Enhancement and Restoration- Image and Video Coding and Compression- Multimodal and Multi-Sensor Models of Image Formation- Image Registration- Segmentation and Grouping- Early and Biologically-Inspired Vision- Color and Texture Analyses- Shape Representation and Matching- Features Extraction- Visual Attention and Image SaliencyArea 3: Image and Video Understanding- Cognitive Models for Interpretation, Integration and Control- Computational Photography- Deep Learning for Visual Understanding - Machine Learning Technologies for Vision- Face and Expression Recognition- Content-Based Indexing, Search, and Retrieval- Object and Face Recognition- Object Detection and Localization- Categorization and Scene Understanding- Event and Human Activity Recognition- Few Shot Learning- Transfer Learning- Domain Adaptation- Multi-task learning- Self-taught LearningArea 4: Mobile and Egocentric Vision for Humans and Robots- Deep Learning for Image-to-Text Translation and Dialogue- Deep Learning for Tracking- 3D Deep Learning- Understanding from Wearable and Mobile Cameras- Mobile and Egocentric Object Detection and Recognition- Mobile and Egocentric Localization- Egocentric Vision for Interaction Understanding- Mobile Vision- First Person Vision- Vision for Robotics- Active VisionArea 5: Motion, Tracking and Stereo Vision- Image-Based Modeling and 3D Reconstruction- Stereo Vision and Structure from Motion- Simultaneous Localization and Mapping- Optical Flow and Motion Analyses- Tracking and Visual Navigation- Video Surveillance and Event DetectionVISAPP CONFERENCE CO-CHAIRS:Jose Braz, Escola Superior de Tecnologia de Setúbal, PortugalKadi Bouatouch, IRISA, University of Rennes 1, FranceVISAPP PROGRAM CO-CHAIRS:Giovanni Maria Farinella, Università di Catania, ItalyPetia Radeva, Universitat de Barcelona, SpainPROGRAM COMMITTEEhttp://www.visapp.visigrapp.org/ProgramCommittee.aspxVISAPP SecretariatAddress: Avenida de S. Francisco Xavier, Lote 7 Cv. CTel: +351 265 520 185Fax: +351 265 520 186Web: http://www.visapp.visigrapp.orge-mail: visapp.secretariat@insticc.org