Today we’re joined by Adriana Kovashka, an Assistant Professor at the University of Pittsburgh.
Subscribe: iTunes / Google Play / Spotify / RSS
In our conversation with Adriana, we explore her visual commonsense research, and how it intersects with her background in media studies. We discuss the idea of shortcuts, or faults in visual question answering data sets that appear in many SOTA results, as well as the concept of masking, a technique developed to assist in context prediction. Adriana then describes how these techniques fit into her broader goal of trying to understand the rhetoric of visual advertisements.
Finally, Adriana shares a bit about her work on robust visual reasoning, the parallels between this research and other work happening around explainability, and the vision for her work going forward.
Connect with Adriana!
- Paper: A Case Study of the Shortcut Effects in Visual Commonsense Reasoning
- Paper: Breaking Shortcuts by Masking for Robust Visual Reasoning
- Paper: Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval
- Human-AI Collaboration for Creativity with Devi Parikh
- Embodied Visual Learning with Kristen Grauman
- Visual Commonsense Reasoning Dataset
- Conceptual Captions Dataset
- Check out our TWIML Presents: series page!
- Register for the TWIML Newsletter
- Check out the official TWIMLcon:AI Platform video packages here!
- Download our latest eBook, The Definitive Guide to AI Platforms!
“More On That Later” by Lee Rosevere licensed under CC By 4.0