video-analysis

A cross-platform video structuring (video analysis) framework based on CV models & mLLM.

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

A collection of computer vision pre-trained models.

Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀

Papers, code and datasets about deep learning and multi-modal learning for video analysis

Learning notes and tooling skills for AI video - AI 视频相关的学习与工具 skill

反推出AI视频的提示词，并配有音频分析功能，可提取视频中的台词文案，并且一句话就可剪辑出你要的视频

Code release for ActionFormer (ECCV 2022)

SiamMOT: Siamese Multi-Object Tracking

⚡ 一款用于自动语音识别 (ASR)、翻译的高性能异步 API。不需要购买Whisper API，使用本地运行的Whisper模型进行推理，并支持多GPU并发，针对分布式部署进行设计。还内置了包括TikTok、抖音等社交媒体平台的爬虫，可实现来自多个社交平台的无缝媒体处理，为媒体内容数据自动化处理提供了强大且可扩展的解决方案。

Official implementation of Paper Future Frame Prediction for Anomaly Detection -- A New Baseline, CVPR 2018

Video-based object counting software.

AI-Powered Video Retrieval & Clipping Tool

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

Library with dynamic audio/video composition and runtime control

Human action classification system with pose-based (MediaPipe) and video-based (3D CNN) models. Features 100+ architectures for real-time pose classification and temporal models pretrained on UCF-101/HMDB51.

Awesome Resources for Advanced Computer Vision Topics

Codebase for CVPR2020 A Local-to-Global Approach to Multi-modal Movie Scene Segmentation