garythung/torch-lrcn

An implementation of the LRCN in Torch

45
/ 100
Emerging

This tool helps researchers and computer vision scientists automatically identify and categorize actions occurring in video footage. You provide a list of video files along with a single label for the primary action in each video. The system then processes this data to train a model that can recognize these actions in new, unseen videos, outputting accuracy metrics for action recognition.

No commits in the last 6 months.

Use this if you need to classify the overall action within an entire video, rather than identifying specific actions at precise moments.

Not ideal if you require frame-by-frame action detection or need to label multiple, distinct actions within a single video.

action-recognition video-analysis computer-vision activity-detection machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

93

Forks

31

Language

Lua

License

MIT

Last pushed

Apr 08, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/garythung/torch-lrcn"

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