Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering

arXiv:2401.10711v3 Announce Type: replace
Abstract: Video Question Answering (VideoQA) aims to answer natural language questions based on the information observed in videos. Despite the recent success of Large Multimodal Models (LMMs) in image-language understanding and reasoning, they deal with VideoQA insufficiently, by simply taking uniformly sampled frames as visual inputs, which ignores question-relevant visual clues. Moreover, there are no human annotations for question-critical timestamps in existing VideoQA datasets. In light of this, we propose a novel weakly supervised framework to …

abstract arxiv cs.ai cs.cl cs.cv deal image information language language understanding large multimodal models lmms multimodal multimodal models natural natural language question question answering questions reasoning success the information type understanding video videos