SUBMISSION INSTRUCTIONS

We solicit submissions of technical papers (5 to 8 pages) and extended abstracts (2 to 4 pages).

Please submit at the FA.DE.TR.CV@CVPR2020 CMT web site

Submitted technical papers and extended abstracts must follow the CVPR paper format and guidelines (see CVPR2020 Author Guidelines ). All accepted submissions must be presented by one of the authors.

Submission deadline for technical papers and extended abstracts is March 20 April 3 2019 11.59pm Pacific Time (see Important Dates below)

We invite submissions of new original work as well as of ongoing or already published work covering novel, paradigm-shifting, groundbreaking ideas and visions for any of the topics relevant to the workshop. Reports on demonstrations and prototypes are also welcome.

Accepted work will be presented as either an oral or a poster presentation. The review will be a double-blind.

TOPICS

We solicit original research papers covering these areas to be submitted to the workshop:

• Vision/AI and bias
• Secure machine learning in vision and AI
• Vision/AI model security using blockchain
• Explainability in Vision/AI decisions
• Analytics in encrypted domain
• Secure Vision/AI computing and blockchain
• Vision/AI provenance and lineage
• Trust in Vision/AI
• Privacy in Vision/AI
• Robustness of Vision/AI models
• Vision/AI forensics
• Vision/AI models attribution
• work that spans across the many dimensions of trust
• Algorithms and theories for learning computer vision models under bias and scarcity
• Methods for exploiting prior knowledge to learn models under bias/scarcity
• Optimization methods designed for learning models from side-channel/alternative/synthetic sources of data
• Domain adaptation methods to bridge train/test data gap
• Methods for studying generalization characteristics of vision models trained from alternative data sources
• Methods of evaluating performance of models under bias/scarcity
• Domain-specific methods designed for important computer vision applications
• Performance characterization of vision algorithms and systems under bias and scarcity.
• Continuous re nement of vision models using active/online learning.
• Meta-learning models from various existing task-speci c models.
• Brave new ideas to learn computer vision models under bias and scarcity
• New algorithms and architectures explicitly designed to reduce bias in visual analytics
• New techniques to balance/manipulate data to reduce bias in visual analytics
• New datasets to improve and measure bias/diversity in visual analytics
• New evaluation protocols to assess and measure bias/diversity in visual analytics
• Generative methods to reduce bias in visual analytics
• Evaluations of bias/diversity of state of the art techniques in visual analytics
• Transfer learning/domain adaptation techniques for more fair visual analytics

IMPORTANT DATES

Workshop paper submission deadline: March 20 April 3, 2020

Paper review period: April 3 - April 10, 2020

Notification to authors: April 12, 2020

Camera ready paper deadline: April 17, 2020

Finalized workshop program: April 20, 2020