University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Question Answering in Realistic Visual Environments: Challenges and Approaches

Question Answering in Realistic Visual Environments: Challenges and Approaches

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Mateja Jamnik.

The Embodied Question Answering (EQA) and Interactive Question Answering (IQA) tasks were recently introduced as a means to study the capabilities of agents in rich, realistic 3D environments, requiring both navigation and reasoning to achieve success. Each of these skills typically needs a different approach, which should nevertheless be smoothly integrated with the rest of the system leveraged by the agent. However, initial approaches either suffer from potentially weaker performance than when using a language-only model or are preceded by additional hand-engineered steps. This talk will provide an overview of the existing work on this thread and describe in more detail our recent study (which I started while being a research intern at Mila last summer) published at BMVC 2019 and to be presented as a spotlight talk at the ViGIL NeurIPS 2019 workshop, VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering. Slides are available here.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity