video-summarization 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
AI 视频解说全流程 skill 包：自动切镜头、看画面写解说词、配音合成成片，支持一键导出可编辑的剪映/CapCut 草稿，无需 GPU ｜ Agent skills that turn videos into narrated recaps & editable CapCut drafts
Unsupervised video summarization with deep reinforcement learning (AAAI'18)
[ICCV 2023] UniVTG: Towards Unified Video-Language Temporal Grounding
Self-hosted AI video analysis: summaries, chapters, keyframes, transcripts and SRT / JSON export. AI 视频总结、字幕提取与结构化分析。
Generate summary of any video 📺 anywhere and anytime
Official pytorch repository for "QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection" (CVPR 2023 Paper)
Python API & command-line tool to easily transcribe speech-based video files into clean text
DSNet: A Flexible Detect-to-Summarize Network for Video Summarization
Implementation of our ECCV 2016 Paper (Video Summarization with Long Short-term Memory)
A new multi-shot video understanding benchmark Shot2Story with comprehensive video summaries and detailed shot-level captions.
Official pytorch repository for CG-DETR "Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Grounding"
AAAI 2018 -采用深度强化学习的无监督视频摘要（Theano）
@MilkyAi at bilibili🥛 开发者互助活动：点击星星收藏本repository，可以凭您的GitHub用户名+“开发者互助”关键词在哔哩哔哩私信@dev_milky（不是@MilkyAi哦）以兑换10日电子邮件笔记用量上限移除~！ 感谢您对Milky的支持！
A PyTorch reimplementation of FCSN in paper "Video Summarization Using Fully Convolutional Sequence Networks"
Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.
The official code of "CSTA: CNN-based Spatiotemporal Attention for Video Summarization"
An AI-powered tool for transcribing, summarizing, and creating smart clips from video and audio content.
WordPilot is a tool that converts YouTube videos into written blog format, with images and export options. It uses natural language processing to automatically transcribe and summarize video content. Suitable for content creators and marketers. Open for contributions and feedback.
VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.