Neural Reasoning, Fast and Slow, for Video Question Answering

By Thao Minh Le, Vuong Le, Svetha Venkatesh, Truyen Tran. 2019

14 citations recorded by the source corpus.

What does it take to design a machine that learns to answer natural questions about a video? A Video QA system must simultaneously understand language, represent visual content over space-time, and iteratively transform these representations in response to lingual content in the query, and finally arriving at a sensible answer. While recent advances in lingual and visual question answering have enabled sophisticated representations and neural reasoning mechanisms, major challenges in Video QA remain on dynamic grounding of concepts, relations and actions to support the reasoning process. Inspired by the dual-process account of human reasoning, we design a dual process neural architecture, which is composed of a question-guided video processing module (System 1, fast and reactive) followed by a generic reasoning module (System 2, slow and deliberative). System 1 is a hierarchical model that encodes visual patterns about objects, actions and relations in space-time given the textual cues from the question. The encoded representation is a set of high-level visual features, which are then passed to System 2. Here multi-step inference follows to iteratively chain visual elements as instructed by the textual elements. The system is evaluated on the SVQA (synthetic) and TGIF-QA datasets (real), demonstrating competitive results, with a large margin in the case of multi-step reasoning.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Question Answering & Reading Comprehension

Citations in the corpus

• Just Ask: Learning to Answer Questions from Millions of Narrated Videos (2020, neutral): “video domain (VideoQA), spatio-temporal video representations in terms of motion and appearance have been used in [22, 26, 31, 33, 34, 35, 40, 41, 42, 48, 84, 86, 94, 102].”
• Hierarchical Conditional Relation Networks for Multimodal Video Question Answering (2020, unknown): “non-local operators [25,26]. Within the second approach, the TRN network [27] demonstrates the role of temporal frame relations as an another important visual feature for video reasoning and Video QA [28]. Relations of 4 Le et al. predetected objects were also considered in a separate processing str”
• Zero-Shot Video Question Answering via Frozen Bidirectional Language Models (2022, unknown): “[50] Thao Minh Le, Vuong Le, Svetha Venkatesh, and Truyen Tran.”