ai-agent

video-classification: Master Action Recognition with 3D CNNs and RNNs

Name: video-classification: Master Action Recognition with 3D CNNs and RNNs
Author: HHTseng

A step‑by‑step Jupyter Notebook that shows founders how to build video classification models on UCF101 using PyTorch, 3D CNNs, and CNN‑RNN hybrids.

From the repo · “Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101”

970 stars217 forksJupyter NotebookGuide quality 8/10 · reviewed Oct 7Updated 12/7/2020100% free · open source

What it does

Classify videos into specific human actions using 3D CNN or CNN+RNN architectures on the UCF101 dataset

When to use it

•Building a smart home security system that detects human activities
•Creating an application for automated sports analysis
•Developing a healthcare tool for monitoring patient activity levels

Ready-to-paste prompt

python3D_CNN.py --dataset UCF101 --model 3D_CNN --epochs 10 --batch_size 32

Heads up: Ensure you have the necessary GPU resources and a compatible CUDA version to run the 3D CNN model, as specified in the README

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/video-classification && curl -fsSL https://workflowstacks.com/api/skills/video-classification/claude-skill -o ~/.claude/skills/video-classification/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How video-classification: Master Action Recognition with 3D CNNs and RNNs works

Codeflow

Free to inspect

Video-classification: Master Action Recognition with 3D CNNs and RNNs is mostly documents (1 doc file, 12 small scripts) — something you read, not something you run. There is nothing to install. Last commit 72 months ago, no license file.

Size

Mostly documents

1 document · 12 small scripts · 2 min skim

Setup

Nothing to install

A course / notebook collection. Read it; run cells if you like.

Runs on

Nowhere — you read it

A reading resource, not a program.

Jupyter Notebook 98%Python 2%

Where to start reading

1
README.md
Start here — what it does and how to install it

What's in each folder

Conv3D/Folder19 files

ResNetCRNN/Folder17 files

ResNetCRNN_varylength/Folder16 files

CRNN/Folder14 files

fig/Folder8 files

READMENo licenseLast update 72 mo ago

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/video-classification && curl -fsSL https://workflowstacks.com/api/skills/video-classification/claude-skill -o ~/.claude/skills/video-classification/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

HHTseng

Language

Jupyter Notebook

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Automate your meeting summaries

A private form takes any transcript (from Zoom, Meet, Otter, Fireflies) and emails you back a structured summary: a TL;DR, the decisions made, and action items with owners.

Outcome guide

Reduce meeting no-shows automatically

Keep your meetings in a Google Sheet. Every morning the workflow emails a warm, confirming reminder to anyone scheduled for the next day — automatically, in your voice.