Awesome
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
Overview
This package is a TensorFlow implementation of the paper W-TALC: Weakly-supervised Temporal Activity Localization and Classification, by Sujoy Paul, Sourya Roy and Amit K Roy-Chowdhury and published at ECCV 2018. The PyTorch implementation can be found here.
Dependencies
This package uses or depends on the the following packages:
- TensorFlow 1.5
- Python 2.7
- numpy, scipy among others
Data
The Kinetics pre-trained I3D features for Thumos14 dataset can be downloaded here. The annotations are included with this package.
Running
This code can be run using two diferent datasets - Thumos14 and Thumos14reduced. The later dataset contain only the data points which has temporal boundaries. The dataset name (with other parameters can be changed in options.py). The file to be executed is train.py. The detection results can be viewed in the text file named .log generated during execution.
Citation
Please cite the following work if you use this package.
@inproceedings{paul2018w,
title={W-TALC: Weakly-supervised Temporal Activity Localization and Classification},
author={Paul, Sujoy and Roy, Sourya and Roy-Chowdhury, Amit K},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
pages={563--579},
year={2018}
}
Contact
Please contact the first author of the associated paper - Sujoy Paul (supaul@ece.ucr.edu) for any further queries.