It is our great pleasure to welcome you to the 1st International Workshop on Trustworthy AI for Multimedia Computing, being held with 2021 ACM Multimedia Conference. Artificial Intelligence technologies have been widely adopted in various computer systems including many multimedia applications. Meanwhile, various trustworthy AI problems arising during the development and deployment of the AI applications have been receiving increasing attentions from both academia and industry. These trustworthy topics include model Robustness & Safety, Fairness, Data Privacy, Explainability, Accountability and Transparency.
Proceeding Downloads
An Empirical Study of Uncertainty Gap for Disentangling Factors
Disentangling factors has proven to be crucial for building interpretable AI systems. Disentangled generative models would have explanatory input variables to increase the trustworthiness and robustness. Previous works apply a progressive ...
Patch Replacement: A Transformation-based Method to Improve Robustness against Adversarial Attacks
Deep Neural Networks (DNNs) are robust against intra-class variability of images, pose variations and random noise, but vulnerable to imperceptible adversarial perturbations that are well-crafted precisely to mislead. While random noise even of ...
Dataset Diversity: Measuring and Mitigating Geographical Bias in Image Search and Retrieval
Many popular visual datasets used to train deep neural networksfor computer vision applications, especially for facial analytics,are created by retrieving images from the internet. Search enginesare often used to perform this task. However, due to ...
Hierarchical Semantic Enhanced Directional Graph Network for Visual Commonsense Reasoning
Visual commonsense reasoning (VCR) task aims at boosting research of cognition-level correlations reasoning. It requires not only a thorough understanding of correlated details of the scene but also the ability to infer correlation with related ...
- Proceedings of the 1st International Workshop on Trustworthy AI for Multimedia Computing