paper-with-me

홈 › Papers

Frame-Subtitle Self-Supervision for Multi-Modal Video Question Answering

2022-09-08 · Jiong Wang, Zhou Zhao, Weike Jin

Multi-modal video question answering aims to predict correct answer and localize the temporal boundary relevant to the question. The temporal annotations of questions improve QA performance and interpretability of recent works, but they are usually empirical and costly. To avoid the temporal annotations, we devise a weakly supervised question grounding (WSQG) setting, where only QA annotations are used and the relevant temporal boundaries are generated according to the temporal attention scores. To substitute the temporal annotations, we transform the correspondence between frames and subtitles to Frame-Subtitle (FS) self-supervision, which helps to optimize the temporal attention scores and hence improve the video-language understanding in VideoQA model. The extensive experiments on TVQA and TVQA+ datasets demonstrate that the proposed WSQG strategy gets comparable performance on question grounding, and the FS self-supervision helps improve the question answering and grounding performance on both QA-supervision only and full-supervision settings.

📄 PDF Abstract BibTeX arXiv:2209.03609

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringVideo Question Answering

Similar Papers 제목 키워드 기반

Watch and Learn: Mapping Language and Noisy Real-world Videos with Self-supervision

2020-11-19 · Yujie Zhong, Linhai Xie, Sen Wang, Lucia Specia 외

In this paper, we teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations. Firstly, we define a self-supervised learning f…

RetrievalSelf-Supervised Learning

Gaining Extra Supervision via Multi-task learning for Multi-Modal Video Question Answering

2019-05-28 · Junyeong Kim, Minuk Ma, Kyung-Su Kim, Sungjin Kim 외

This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task that aims at the joint understanding of v…

Inductive BiasMetric LearningMulti-Task LearningQuestion Answering+3

HowToCaption: Prompting LLMs to Transform Video Annotations at Scale

2023-10-07 · Nina Shvetsova, Anna Kukleva, Xudong Hong, Christian Rupprecht 외

Instructional videos are a common source for learning text-video or even multimodal representations by leveraging subtitles extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. H…

Automatic Speech RecognitionVideo CaptioningVideo RetrievalZero-Shot Video-Audio Retrieval+1

What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions

2024-01-01 · CVPR 2024 1 · Brian Chen, Nina Shvetsova, Andrew Rouditchenko, Daniel Kondermann 외

Spatio-temporal grounding describes the task of localizing events in space and time e.g. in video data based on verbal descriptions only. Models for this task are usually trained with human-annotated sentences and bo…

Representation Learning

What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions

2023-03-29 · Brian Chen, Nina Shvetsova, Andrew Rouditchenko, Daniel Kondermann 외

Spatio-temporal grounding describes the task of localizing events in space and time, e.g., in video data, based on verbal descriptions only. Models for this task are usually trained with human-annotated sentences and bou…

Representation LearningSpatio-Temporal Video Grounding