csiro-robotics/TCE
This repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).
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.
Stars
53
Forks
1
Language
Python
License
—
Category
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.
Higher-rated alternatives
cosmosgl/graph
GPU-accelerated force graph layout and rendering
Clay-foundation/model
The Clay Foundation Model - An open source AI model and interface for Earth
nomic-ai/nomic
Nomic Developer API SDK
omoindrot/tensorflow-triplet-loss
Implementation of triplet loss in TensorFlow
sashakolpakov/dire-jax
DImensionality REduction in JAX