This repository is the official implementation of SAC. In this work, we tackle the temporal action localization task from the perspective of modality, and precisely assign frame-modality attention. Paper from arXiv or IEEE.

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:6666)

Please ensure the data structure is as below

├── data
   └── thumos
       └── val
           ├── video_validation_0000051_02432.npz
           ├── video_validation_0000051_02560.npz
           ├── ...
       └── test
           ├── video_test_0000004_00000.npz
           ├── video_test_0000004_00256.npz
           ├── ...

a. Config

Adjust configurations.

./experiments/thumos/network.yaml

c. Train

cd tools
bash run.sh

a. You can download pre-trained models from baiduyun (code:6666), and put the weight file in the folder checkpoint.

• Performance

b. Test

cd tools
python eval.py

• BackTAL: Background-Click Supervision for Temporal Action Localization.
• A2Net: Revisiting Anchor Mechanisms for Temporal Action Localization.

For any discussions, please contact [email protected].