daniel-code/TubeViT

An unofficial implementation of TubeViT in "Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning"

37
/ 100
Emerging

This project helps researchers and developers working with video data to efficiently train and evaluate models for video understanding tasks. You provide a dataset of video clips, and it produces a trained model capable of classifying the actions or content within those videos. This is designed for machine learning practitioners focused on video analysis.

No commits in the last 6 months.

Use this if you need to train a video classification model on a custom dataset, especially if you're exploring the TubeViT architecture for action recognition.

Not ideal if you're looking for a simple tool to analyze videos without any machine learning setup or if you require an out-of-the-box inference solution without training.

video-classification action-recognition machine-learning-research computer-vision deep-learning-models
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

94

Forks

9

Language

Python

License

MIT

Last pushed

Sep 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/daniel-code/TubeViT"

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