paper-with-me

Papers

TVQA: Localized, Compositional Video Question Answering

2018-09-05 · EMNLP 2018 10 · Jie Lei, Licheng Yu, Mohit Bansal, Tamara L. Berg

Recent years have witnessed an increasing interest in image-based question-answering (QA) tasks. However, due to data limitations, there has been much less work on video-based QA. In this paper, we present TVQA, a large-scale video QA dataset based on 6 popular TV shows. TVQA consists of 152,545 QA pairs from 21,793 clips, spanning over 460 hours of video. Questions are designed to be compositional in nature, requiring systems to jointly localize relevant moments within a clip, comprehend subtitle-based dialogue, and recognize relevant visual concepts. We provide analyses of this new dataset as well as several baselines and a multi-stream end-to-end trainable neural network framework for the TVQA task. The dataset is publicly available at http://tvqa.cs.unc.edu.

📄 PDF Abstract BibTeX arXiv:1809.01696

Code (4)

BM-K/Question-Difficulty-Estimation pytorch
h19920918/quiz_for_day06
jayleicn/TVQA pytorch
mansigoel/TVQA pytorch

Tasks

Video Question Answering

Similar Papers 제목 키워드 기반

TVQA+: Spatio-Temporal Grounding for Video Question Answering

2019-04-25 · ACL 2020 6 · Jie Lei, Licheng Yu, Tamara L. Berg, Mohit Bansal

We present the task of Spatio-Temporal Video Question Answering, which requires intelligent systems to simultaneously retrieve relevant moments and detect referenced visual concepts (people and objects) to answer natural…

Question AnsweringVideo Question Answering

SFA: Scan, Focus, and Amplify toward Guidance-aware Answering for Video TextVQA

2025-11-25 · Haibin He, Qihuang Zhong, Juhua Liu, Bo Du 외 arxiv

Video text-based visual question answering (Video TextVQA) task aims to answer questions about videos by leveraging the visual text appearing within the videos. This task poses significant challenges, requiring models to…

Visual Question Answering

Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues

2024-12-17 · Yan Zhang, Gangyan Zeng, Huawen Shen, Daiqing Wu 외

Video text-based visual question answering (Video TextVQA) is a practical task that aims to answer questions by jointly reasoning textual and visual information in a given video. Inspired by the development of TextVQA in…

Language ModelingLanguage ModellingOptical Character Recognition (OCR)Question Answering+2

Reading Between the Lanes: Text VideoQA on the Road

2023-07-08 · George Tom, Minesh Mathew, Sergi Garcia, Dimosthenis Karatzas 외

Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem, while textual cues typically appear for…

Question AnsweringScene Text RecognitionVideo Question Answering

VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA

2026-05-06 · Haibin He, Maoyuan Ye, Jing Zhang, Juhua Liu 외 arxiv

Video text-based visual question answering (Video TextVQA) aims to answer questions by reasoning over visual textual content appearing in videos. Despite the strong multimodal video understanding capabilities of recent V…

Visual Question AnsweringReinforcement Learning