chuckcho/video-caffe
Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data
This project helps researchers and engineers working with video data to analyze and classify actions within those videos. It takes raw video files or extracted video frames as input and, through a process of deep learning, outputs classifications of actions (like 'playing tennis' or 'baking a cake') that occur in the videos. It is ideal for those involved in computer vision research, particularly in action recognition.
176 stars. No commits in the last 6 months.
Use this if you need to train a robust deep learning model to recognize specific actions in video footage, especially if you're working with datasets like UCF-101.
Not ideal if you are looking for a simple, off-the-shelf video classification tool without deep learning model training, or if you don't have experience with deep learning frameworks and GPU acceleration.
Stars
176
Forks
91
Language
C++
License
—
Category
Last pushed
Dec 24, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/chuckcho/video-caffe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ra1nty/DXcam
A Python high-performance screen capture library for Windows using Desktop Duplication API - Updated 2026
alan-turing-institute/scivision
scivision: a framework for scientific image analysis
jishnujayakumar/MV-Tractus
A simple tool to extract motion vectors from h264 encoded videos.
LionelJouin/PiP-Tool
PiP tool is a software to use the Picture in Picture mode on Windows. This feature allows you to...
cmusatyalab/OpenTPOD
Open Toolkit for Painless Object Detection