Colar: Effective and Efficient Online Action Detection by Consulting Exemplars
This repository is the official implementation of Colar. In this work, we study the online action detection and develop an effective and efficient exemplar-consultation mechanism. Paper from arXiv.
To install requirements:
conda env create -n env_name -f environment.yaml
Before running the code, please activate this conda environment.
a. Download pre-extracted features from baiduyun (code:cola)
Please ensure the data structure is as below
├── data
└── thumos14
├── Exemplar_Kinetics
├── thumos_all_feature_test_Kinetics.pickle
├── thumos_all_feature_val_Kinetics.pickle
├── thumos_test_anno.pickle
├── thumos_val_anno.pickle
├── data_info.json
a. Config
Adjust configurations according to your machine.
./misc/init.py
c. Train
python main.py
a. You can download pre-trained models from baiduyun (code:cola), and put the weight file in the folder checkpoint
.
b. Test
python inference.py
@inproceedings{yang2022colar,
title={Colar: Effective and Efficient Online Action Detection by Consulting Exemplars},
author={Yang, Le and Han, Junwei and Zhang, Dingwen},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2022}
}
Author: VividLe
Source: https://github.com/VividLe/Online-Action-Detection