transnetv2-scene-detect

Community

High-precision scene detection for local video

Authorqianleigood
Version1.0.0
Installs0

System Documentation

What problem does it solve?

TransNetV2-based scene detection enables accurate identification of shot boundaries and scene cuts in video workflows, removing manual frame-by-frame annotations.

Core Features & Use Cases

  • High-accuracy shot boundary detection for video segmentation.
  • Local preprocessing and cutting to support downstream analysis and archiving.
  • Shot JSON generation to feed into video-analysis pipelines and workflows like video-analysis-workflow.

Quick Start

Run the main entry with run.sh, ensure weights exist at assets/weights/transnetv2-pytorch-weights.pth, and write outputs to output/ with stable script and asset paths.

Dependency Matrix

Required Modules

torchopencv-pythonscenedetectnumpyrequestspython-docxffmpeg-python

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: transnetv2-scene-detect
Download link: https://github.com/qianleigood/crawclaw/archive/main.zip#transnetv2-scene-detect

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.