Watching the News: Towards VideoQA Models that can Read

Soumya Jahagirdar*, Minesh Mathew, Dimosthenis Karatzas, C. V. Jawahar

*Corresponding author for this work

Research output: Chapter in BookChapterResearchpeer-review

2 Citations (Scopus)

Abstract

Video Question Answering methods focus on common-sense reasoning and visual cognition of objects or persons and their interactions over time. Current VideoQA approaches ignore the textual information present in the video. Instead, we argue that textual information is complementary to the action and provides essential contextualisation cues to the reasoning process. To this end, we propose a novel VideoQA task that requires reading and understanding the text in the video. To explore this direction, we focus on news videos and require QA systems to comprehend and answer questions about the topics presented by combining visual and textual cues in the video. We introduce the "NewsVideoQA"dataset that comprises more than 8, 600 QA pairs on 3, 000+ news videos obtained from diverse news channels from around the world. We demonstrate the limitations of current Scene Text VQA and VideoQA methods and propose ways to incorporate scene text information into VideoQA methods.

Original languageEnglish
Title of host publicationWACV
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4430-4439
Number of pages10
ISBN (Electronic)9781665493468
ISBN (Print)9781665493468
DOIs
Publication statusPublished - 2023

Publication series

NameProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023

Keywords

  • Algorithms: Vision + language and/or other modalities
  • Arts/games/social media
  • Video recognition and understanding (tracking, action recognition, etc.)

Fingerprint

Dive into the research topics of 'Watching the News: Towards VideoQA Models that can Read'. Together they form a unique fingerprint.

Cite this