VidChapters-7M: Video Chapters at Scale

TL;DR

This paper introduces VidChapters-7M, a large-scale dataset of user-annotated video chapters, and proposes tasks for automatic video chapter segmentation and localization, demonstrating its effectiveness for pretraining and improving related video understanding tasks.

Contribution

The paper presents VidChapters-7M, a novel large-scale dataset for video chaptering, along with new tasks and benchmarks, enabling scalable research in video segmentation and captioning.

Findings

Pretraining on VidChapters-7M improves dense video captioning performance.

Models trained on this dataset generalize well to other benchmarks.

Performance scales positively with dataset size.

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. Our dataset, code, and models are publicly available at https://antoyang.github.io/vidchapters.html.