csiro-robotics/TCE

This repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).

19
/ 100
Experimental

This project helps researchers and developers working in computer vision to train models that understand actions in videos, even with limited labeled data. It takes video frames as input and produces a trained model capable of classifying specific actions like 'bowling'. The primary users are machine learning researchers focused on self-supervised learning for video analysis.

No commits in the last 6 months.

Use this if you need to train robust video action recognition models without extensive manual annotation, leveraging self-supervised learning techniques.

Not ideal if you are looking for a plug-and-play solution for general video analysis without any coding or model training.

video-analysis action-recognition computer-vision machine-learning-research deep-learning-training
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 3 / 25

How are scores calculated?

Stars

53

Forks

1

Language

Python

License

Last pushed

Mar 16, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/csiro-robotics/TCE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.