A PyTorch implementation of RSC based on MMM 2023 paper Weakly-supervised Temporal Action Localization with Regional Similarity Consistency.
Git clone the corresponding repos and replace the files provided by us, then run the code according to readme of
corresponding repos.
For example, to train HAM-Net on THUMOS14 dataset:
git clone https://github.com/asrafulashiq/hamnet.git
mv AGCT/hamnet/* hamnet/
python main.py
To evaluate HAM-Net on THUMOS14 dataset:
python main.py --test --ckpt [checkpoint_path]
The models are trained on one NVIDIA GeForce GTX 1080 Ti (11G). All the hyper-parameters are the default values. Here we provide the pre-trained models on THUMOS14 dataset.
| Method | THUMOS14 | Download | |||||||
|---|---|---|---|---|---|---|---|---|---|
| mAP@0.1 | mAP@0.2 | mAP@0.3 | mAP@0.4 | mAP@0.5 | mAP@0.6 | mAP@0.7 | mAP@AVG | ||
| HAM-Net | 66.9 | 60.2 | 51.0 | 42.0 | 31.7 | 22.1 | 12.0 | 40.9 | OneDrive |
| CoLA | 67.2 | 61.5 | 52.9 | 43.9 | 34.8 | 24.9 | 13.0 | 42.6 | OneDrive |
| CO2-Net | 70.6 | 64.2 | 55.9 | 47.7 | 38.9 | 26.0 | 13.6 | 45.3 | OneDrive |
mAP@AVG is the average mAP under the thresholds 0.1:0.1:0.7.
