Prompt-Driven Agentic Video Editing System: Autonomous Comprehension of Long-Form, Story-Driven Media

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ding, Zihan, Wang, Xinyi, Chen, Junlong, Kristensson, Per Ola, Shen, Junxiao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914060601131008
author Ding, Zihan
Wang, Xinyi
Chen, Junlong
Kristensson, Per Ola
Shen, Junxiao
author_facet Ding, Zihan
Wang, Xinyi
Chen, Junlong
Kristensson, Per Ola
Shen, Junxiao
contents Creators struggle to edit long-form, narrative-rich videos not because of UI complexity, but due to the cognitive demands of searching, storyboarding, and sequencing hours of footage. Existing transcript- or embedding-based methods fall short for creative workflows, as models struggle to track characters, infer motivations, and connect dispersed events. We present a prompt-driven, modular editing system that helps creators restructure multi-hour content through free-form prompts rather than timelines. At its core is a semantic indexing pipeline that builds a global narrative via temporal segmentation, guided memory compression, and cross-granularity fusion, producing interpretable traces of plot, dialogue, emotion, and context. Users receive cinematic edits while optionally refining transparent intermediate outputs. Evaluated on 400+ videos with expert ratings, QA, and preference studies, our system scales prompt-driven editing, preserves narrative coherence, and balances automation with creator control.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16811
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt-Driven Agentic Video Editing System: Autonomous Comprehension of Long-Form, Story-Driven Media
Ding, Zihan
Wang, Xinyi
Chen, Junlong
Kristensson, Per Ola
Shen, Junxiao
Artificial Intelligence
Human-Computer Interaction
Creators struggle to edit long-form, narrative-rich videos not because of UI complexity, but due to the cognitive demands of searching, storyboarding, and sequencing hours of footage. Existing transcript- or embedding-based methods fall short for creative workflows, as models struggle to track characters, infer motivations, and connect dispersed events. We present a prompt-driven, modular editing system that helps creators restructure multi-hour content through free-form prompts rather than timelines. At its core is a semantic indexing pipeline that builds a global narrative via temporal segmentation, guided memory compression, and cross-granularity fusion, producing interpretable traces of plot, dialogue, emotion, and context. Users receive cinematic edits while optionally refining transparent intermediate outputs. Evaluated on 400+ videos with expert ratings, QA, and preference studies, our system scales prompt-driven editing, preserves narrative coherence, and balances automation with creator control.
title Prompt-Driven Agentic Video Editing System: Autonomous Comprehension of Long-Form, Story-Driven Media
topic Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2509.16811