# Zero-Shot Long-Form Video Understanding through Screenplay

Source: [Zero-Shot Long-Form Video Understanding through Screenplay](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea87>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:58:03.881Z

Authors: Yongliang Wu, Bozheng Li, Jiawang Cao, Wenbo Zhu, Yi Lu, Weiheng Chi, Chuyun Xie, Haolin Zheng, Ziyue Su, Jay Wu, Xu Yang

Published: 2024-06-25T06:42:26.000Z

## Abstract

The Long-form Video Question-Answering task requires the comprehension and analysis of extended video content to respond accurately to questions by utilizing both temporal and contextual information. In this paper, we present MM-Screenplayer, an advanced video understanding system with multi-modal perception capabilities that can convert any video into textual screenplay representations. Unlike previous storytelling methods, we organize video content into scenes as the basic unit, rather than just visually continuous shots. Additionally, we developed a \`\`Look Back'' strategy to reassess and validate uncertain information, particularly targeting breakpoint mode. MM-Screenplayer achieved highest score in the CVPR'2024 LOng-form VidEo Understanding (LOVEU) Track 1 Challenge, with a global accuracy of 87.5% and a breakpoint accuracy of 68.8%.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.17309>)

[PDF](<https://arxiv.org/pdf/2406.17309.pdf>)
