AI Paper Atlas

Research map / Video / Video generation

MEV: A Multi-Event Video Dataset for Long-Take Generation

Peiyuan Zhu, Shaoan Xie, Yifan Shen, Wen Tian, Zijian Li, Guangyi Chen, Kun Zhang

NeurIPS 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces MEV, a multi-event video dataset intended to supervise long-take text-to-video generation with temporally consistent multi-event descriptions.

Problem

Existing text-to-video datasets mostly contain short single-event clips or coarse captions, giving little supervision for long-take temporal dependencies and causing inconsistencies when multiple events are described.

Approach

A dataset of multi-event videos with event-level annotations aimed at training and evaluating long-take generation; the abstract mentions only the dataset's motivation, not its specific construction.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune Wan2.1-1.3B on MEV (verified events, grounded boundaries) instead of an UltraVideo-Long subset with uniform boundaries (ablation)MinT-style multi-event Wan adaptation · MEV-EvalEOA: 0.33 -> 0.45Improved
fine-tune on MEV with grounded event conditioning instead of Ultra-Wan data (ablation)MinT-style multi-event Wan adaptation · MEV-EvalTGA: 0.42 -> 0.60Improved
fine-tune on MEV with grounded event conditioning instead of Ultra-Wan data (ablation)MinT-style multi-event Wan adaptation · MEV-EvalBTC: 0.50 -> 0.64Improved
multi-event fine-tuning on MEV added to base Wan2.1-1.3BWan2.1-1.3B · MEV-EvalEEA: 0.42 -> 0.61Improved
multi-event fine-tuning on MEV added to base Wan2.1-1.3BWan2.1-1.3B · MEV-EvalEOA: 0.20 -> 0.45Improved
fine-tune on MEV instead of Ultra-Wan data (ablation)MinT-style multi-event Wan adaptation · MEV test set VBenchImaging Quality: 63.328 -> 64.924Improved
fine-tune on MEV instead of Ultra-Wan data (ablation)MinT-style multi-event Wan adaptation · MEV test set VBenchSubject Consistency: 0.936 -> 0.960Improved
multi-event fine-tuning on MEV added to base Wan2.1-1.3BWan2.1-1.3B · MEV test set VBenchMotion Smoothness: 0.991 -> 0.991No clear effect
multi-event fine-tuning on MEV added to base Wan2.1-1.3BWan2.1-1.3B · MEV test set VBenchAesthetic Quality: 0.585 -> 0.590No clear effect
use Gemini 2.5 Pro instead of Qwen3-VL for camera-motion annotation (ablation)MEV annotation pipeline · camera-motion labels, manual evaluationexact-set accuracy: 10% -> 22%Improved
autoregressive prompt-switching (LongLive) instead of MEV-grounded fine-tuningWan2.1-1.3B · MEV-Eval and VBenchAesthetic Quality: 0.585 -> 0.504Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy