LeonHLJ/RSKP
The official implementation of 'Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation' (CVPR 2022)
This project helps video analysts automatically pinpoint when specific actions occur within long, untrimmed videos. You provide video data and general labels for the types of actions you're looking for, and it outputs the precise start and end times for each detected action. This is ideal for researchers or data scientists working with large video datasets for content analysis.
No commits in the last 6 months.
Use this if you need to identify the exact temporal boundaries of actions in videos without having to manually label every single moment of every action.
Not ideal if you need to detect objects or actions in still images, or if your primary goal is general video classification rather than precise temporal localization.
Stars
46
Forks
10
Language
Python
License
MIT
Category
Last pushed
Nov 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LeonHLJ/RSKP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patrick-llgc/Learning-Deep-Learning
Paper reading notes on Deep Learning and Machine Learning
magicleap/SuperGluePretrainedNetwork
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
eric-yyjau/pytorch-superpoint
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629
lucasb-eyer/pydensecrf
Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.
changhao-chen/deep-learning-localization-mapping
A collection of deep learning based localization models