PyTorch Implementation of paper accepted by CVPR'21:
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning
Can Zhang, Meng Cao, Dongming Yang, Jie Chen and Yuexian Zou*.
-
[21 July 2021]
- We have released the codebase and models of our CoLA.
- Note that we have fine-tuned some hyper-parameter settings so the experimental result is better (+2.1% mAP@0.5, +0.8% mAP@AVG) than the orignal paper! Details are as follows:
CoLA mAP@tIoU(%) 0.1 0.2 0.3 0.4 0.5 0.6 0.7 AVG original paper 66.2 59.5 51.5 41.9 32.2 22.0 13.1 40.9 this codebase 66.1 60.0 52.1 43.1 34.3 23.5 13.1 41.7 gain(Δ) -0.1 +0.5 +0.6 +1.2 +2.1 +1.5 0.0 +0.8 - [Results Reproducible] You can get the above results without changing any line of our code.
Please make sure Python>=3.6 is installed (Anaconda3 is recommended).
Required packges are listed in requirements.txt. You can install them by running:
pip install -r requirements.txt
-
Get the code. Clone this repo with git:
git clone https://github.com/zhang-can/CoLA
-
Prepare the features.
- Here, we provide the two-stream I3D features for THUMOS'14. You can download them from Google Drive or Weiyun.
- Unzip the downloaded features into the
data
folder. Make sure the data structure is as below.
├── data └── THUMOS14 ├── gt.json ├── split_train.txt ├── split_test.txt └── features ├── ...
- Note that these features are originally from this repo.
You can use the following command to train CoLA:
python main_moco.py train
After training, you will get the results listed in this table.
You can evaluate a trained model by running:
python main_moco.py test MODEL_PATH
Here, MODEL_PATH
denotes for the path of the trained model.
This script will report the localization performance in terms of mean average precision (mAP) at different tIoU thresholds.
You can download our trained model from Google Drive or Weiyun.
This repository is inspired by the following baseline implementations for the WS-TAL task.
Please [★star] this repo and [cite] the following paper if you feel our CoLA useful to your research:
@InProceedings{zhang2021cola,
author = {Zhang, Can and Cao, Meng and Yang, Dongming and Chen, Jie and Zou, Yuexian},
title = {CoLA: Weakly-Supervised Temporal Action Localization With Snippet Contrastive Learning},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021},
pages = {16010-16019}
}
For any questions, please feel free to open an issue or contact:
Can Zhang: zhang.can.pku@gmail.com