davide-coccomini/TimeSformer-Video-Classification
The notebook explains the various steps to obtain the results of publication: "Is Space-Time Attention All You Need for Video Understanding?"
This project helps researchers and machine learning practitioners analyze and classify actions within video recordings. By inputting video data, you can train a model to accurately categorize different activities, producing classifications for various segments of the video. It's ideal for those working on academic research or applied projects in video understanding.
No commits in the last 6 months.
Use this if you need to build or experiment with state-of-the-art video classification models, particularly for research on attention-based methods.
Not ideal if you're looking for an out-of-the-box, production-ready video analysis tool without any coding or model training.
Stars
42
Forks
7
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/davide-coccomini/TimeSformer-Video-Classification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action