Deep Neural Networks for Visual Reasoning
This work addresses the problem of enabling machines to reason across vision and language modalities, which is crucial for applications like robot-human collaboration, though it appears incremental as it builds on existing deep learning representations.
The thesis tackled the challenge of multimodal reasoning between vision and language by developing mechanisms for content selection and temporal relation construction from dynamic visual scenes, and new frameworks for reasoning using visual-linguistic associations, resulting in improved capabilities for tasks like visual question answering.
Visual perception and language understanding are - fundamental components of human intelligence, enabling them to understand and reason about objects and their interactions. It is crucial for machines to have this capacity to reason using these two modalities to invent new robot-human collaborative systems. Recent advances in deep learning have built separate sophisticated representations of both visual scenes and languages. However, understanding the associations between the two modalities in a shared context for multimodal reasoning remains a challenge. Focusing on language and vision modalities, this thesis advances the understanding of how to exploit and use pivotal aspects of vision-and-language tasks with neural networks to support reasoning. We derive these understandings from a series of works, making a two-fold contribution: (i) effective mechanisms for content selection and construction of temporal relations from dynamic visual scenes in response to a linguistic query and preparing adequate knowledge for the reasoning process (ii) new frameworks to perform reasoning with neural networks by exploiting visual-linguistic associations, deduced either directly from data or guided by external priors.