MEV：面向长镜头生成的多事件视频数据集

View PDF HTML (experimental)

Abstract:Current datasets for text-to-video generation are largely limited to short clips depicting a single event or coarse-grained captions. As a result, they provide limited supervision for modeling long-take temporal dependencies, often leading to temporally inconsistent generations when describing multiple events. In this paper, we introduce MEV, a multi-event video dataset designed for long-take video generation. MEV provides high-quality real-world videos where subjects can perform a sequence of distinct, non-overlapping events, featuring precise temporal boundaries and fine-grained procedural annotations. This event-centric discretization reduces confounding factors and enables models to support temporally localized conditioning and build long-take videos from atomic event units. Furthermore, we introduce a comprehensive annotation pipeline that segments videos into temporally grounded events, and generates structured captions at both the global level and the event level. In addition, under an event-centric evaluation protocol, we conduct multi-event generation experiments by fine-tuning on MEV with temporally grounded event conditioning, leading to improved long-take event transitions and more coherent content. We believe this work provides a publicly available resource for multi-event fine-tuning and event-centric evaluation, together with practical insights into learning from temporally structured video-text data.

Comments:	Accepted to NeurIPS 2026. Project page: this https URL
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.38241 [cs.CV]
	(or arXiv:2610.38241v1 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2610.38241 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Peiyuan Zhu [view email]
[v1] Wed, 28 Oct 2026 03:43:19 UTC (35,433 KB)