Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning
- 类型:arxiv
- 标识:2608.26809
- 链接:https://arxiv.org/abs/2608.26809
- 主分类:multimodal
- 形态:method
- 被引:0
- 被引来源:Semantic Scholar + OpenAlex
- S2被引:0
- OpenAlex被引:0
- 影响力被引:0
- TLDR:This work introduces an agentic editing framework that leverages the synergy of Large Language Models (LLMs) and Vision-Language Models (VLMs) to achieve shot-level video decoupling and precise instruction parsing, and constructs MMLVE-Bench, which is an MMLVE-focused dataset characterized by complex real-world spatiotemporal dynamics, high-density heterogeneous instructions, and sparse, random entity distributions.
- OpenAlex ID:W7204597527
- OpenAlex DOI:10.48550/arxiv.2608.26809
- DOI:10.48550/arxiv.2608.26809
- DOI来源:OpenAlex
- 开放获取:green
- 开放获取链接:https://arxiv.org/pdf/2608.26809
- OpenAlex更新:2026-09-04
- 副分类:agent
- 待LLM分类:否
- 标题中文:Thinking on Shots:基于 Agentic 推理的一致性多镜头视频编辑。
- TLDR中文:本文提出一个 Agentic 视频编辑框架,利用 LLM 与 VLM 的协同实现 shot 级视频解耦与精确指令解析,并构建 MMLVE-Bench,一个聚焦 MMLVE 的数据集,具有复杂的真实世界时空动态、高密度异构指令以及稀疏随机的实体分布。
- 来源文件:
- /inbox/tom/_candidates/2026-08-28-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]