The workshop aims to foster research around a timely and crucial topic for the present digitized society: the fairness, accountability, transparency and ethics of multimedia algorithms. The workshop has a strong scientific link with the FAT/ML workshop, satellite of ICML, and the ACM FAT* conference. Differently from FAT/ML, which is anchored in machine learning, the FATE/MM workshop addresses fairness, accountability, transparency and ethics in multimedia processing, retrieval, categorization and applications.
More precisely, we expect submissions covering any topic closely related to the multimedia community AND falling in one (or many) of the following categories:
Models
- Techniques and models for fairness-aware multimedia modeling, multimedia information retrieval, and recommendation.
- Interpretable and explainable models in multimedia.
- Models and frameworks for conducting FATE audits of multimedia systems.
- Models for addressing inclusion and exclusion in multimedia.
Algorithm evaluation
- Qualitative, quantitative, and experimental studies on subjective perceptions of algorithmic bias, unfairness and ethical issues.
- Experimental results of FATE audits of multimedia systems.
- Objective metrics for measuring unfairness and bias in multimedia.
- Generation of human-readable explanations for multimedia models and algorithmic outputs.
- Metrics for measuring inclusiveness in multimedia systems.
Data collection and curation
- Defining, measuring and mitigating problematic biases in multimedia datasets.
- Ethical issues in multimedia data collection processes.
- Improvement of data collection processes to be more fair, diverse, and inclusive.
- Data collection regarding potential unfairness in systems and ethical consequences.
Applications
- Research on fair and transparent multimedia tools and applications
- Ethical design and/or usage of multimedia tools and applications
