Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Hongjie, Dong, Lu, Liu, Yi, Huang, Yifei, Wang, Yali, Wang, Limin, Qiao, Yu
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2312.04817
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912560536616960
author Zhang, Hongjie
Dong, Lu
Liu, Yi
Huang, Yifei
Wang, Yali
Wang, Limin
Qiao, Yu
author_facet Zhang, Hongjie
Dong, Lu
Liu, Yi
Huang, Yifei
Wang, Yali
Wang, Limin
Qiao, Yu
contents Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance on limited-length sub-clips as clues to answer those questions. Meanwhile, previous datasets have limited focus on question type and modality. To remedy this, we introduce LvBench, a Long-form video understanding benchmark for versatile multi-modal question-answering. Our LvBench stands out from existing long-form VideoQA datasets through three key characteristics: 1) Extended temporal durations: We consider videos ranging from 70 seconds to 4 hours, covering single-scene, multi-scene, and full-scene contexts. This design accounts for both video and clue lengths, capturing diverse contextual dynamics. 2) Diverse question types and modalities: LvBench introduces six distinct question types that evaluate various perceptual and cognitive capabilities, utilizing both video frames and subtitles. 3) High-quality annotations: We employ rigorous manual labeling by human annotators. Our dataset comprises 20,061 question-answer pairs sourced from 100 carefully selected movies across diverse genres, annotated collaboratively by multiple individuals. Analysis involving various baselines reveals a consistent trend: the performance of all existing methods significantly deteriorates when video and clue length increases. We expect LvBench to serve as a valuable resource for future works on long-form video understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2312_04817
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering
Zhang, Hongjie
Dong, Lu
Liu, Yi
Huang, Yifei
Wang, Yali
Wang, Limin
Qiao, Yu
Computer Vision and Pattern Recognition
Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance on limited-length sub-clips as clues to answer those questions. Meanwhile, previous datasets have limited focus on question type and modality. To remedy this, we introduce LvBench, a Long-form video understanding benchmark for versatile multi-modal question-answering. Our LvBench stands out from existing long-form VideoQA datasets through three key characteristics: 1) Extended temporal durations: We consider videos ranging from 70 seconds to 4 hours, covering single-scene, multi-scene, and full-scene contexts. This design accounts for both video and clue lengths, capturing diverse contextual dynamics. 2) Diverse question types and modalities: LvBench introduces six distinct question types that evaluate various perceptual and cognitive capabilities, utilizing both video frames and subtitles. 3) High-quality annotations: We employ rigorous manual labeling by human annotators. Our dataset comprises 20,061 question-answer pairs sourced from 100 carefully selected movies across diverse genres, annotated collaboratively by multiple individuals. Analysis involving various baselines reveals a consistent trend: the performance of all existing methods significantly deteriorates when video and clue length increases. We expect LvBench to serve as a valuable resource for future works on long-form video understanding.
title LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.04817