VidChapters-7M: Video Chapters at Scale - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

VidChapters-7M: Video Chapters at Scale

Abstract

Segmenting long videos into chapters enables users to quickly navigate to the information of their interest. This important topic has been understudied due to the lack of publicly released datasets. To address this issue, we present VidChapters-7M, a dataset of 817K user-chaptered videos including 7M chapters in total. VidChapters-7M is automatically created from videos online in a scalable manner by scraping user-annotated chapters and hence without any additional manual annotation. We introduce the following three tasks based on this data. First, the video chapter generation task consists of temporally segmenting the video and generating a chapter title for each segment. To further dissect the problem, we also define two variants of this task: video chapter generation given ground-truth boundaries, which requires generating a chapter title given an annotated video segment, and video chapter grounding, which requires temporally localizing a chapter given its annotated title. We benchmark both simple baselines and state-of-the-art video-language models for these three tasks. We also show that pretraining on VidChapters-7M transfers well to dense video captioning tasks in both zero-shot and finetuning settings, largely improving the state of the art on the YouCook2 and ViTT benchmarks. Finally, our experiments reveal that downstream performance scales well with the size of the pretraining dataset.
Fichier principal
Vignette du fichier
view.pdf (8.49 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04217697 , version 1 (26-09-2023)

Identifiers

Cite

Antoine Yang, Arsha Nagrani, Ivan Laptev, Josef Sivic, Cordelia Schmid. VidChapters-7M: Video Chapters at Scale. NeurIPS 2023 - Conference on Neural Information Processing Systems - Track on Datasets and Benchmarks, Dec 2023, New Orleans (LA), United States. ⟨hal-04217697⟩
133 View
51 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More