Abstract
This talk will be introducing our recent paper, VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering. Here, we investigate the feasibility of EQA -type tasks by building a novel benchmark, which contains pairs of questions and videos generated in the House3D environment. While removing the navigation and action selection requirements from EQA , we increase the difficulty of the visual reasoning component via a much larger question space, tackling the sort of complex reasoning questions that make QA tasks challenging. By designing and evaluating several VQA -style models on the dataset, we establish a novel way of evaluating EQA feasibility given existing methods, while highlighting the difficulty of the problem even in the most ideal setting.
Dr Cătălina Cangea
Senior Research Scientist
Senior Research Scientist at Google DeepMind, with a PhD in ML from the University of Cambridge, and inhaler of music :) Focus on generative music models, finding signals in data and human evaluation. Motivated by contributing ML-based knowledge and improvements to real-world systems!