Grouped Spatial-Temporal Aggretation for Efficient Action Recognition

Pytorch implementation of paper Grouped Spatial-Temporal Aggretation for Efficient Action Recognition. arxiv

Prerequisites

• PyTorch 1.0 or higher
• python 3.5 or higher

Data preparation

Please refer to TRN-pytorch for data preparation on Something-Something.

Training

• For GST-Large: python3 main.py --root_path /path/to/video/folder --dataset somethingv1 --checkpoint_dir /path/for/saving/checkpoints/ --type GST --arch resnet50 --num_segments 8 --beta 1
• For GST: python3 main.py --root_path /path/to/video/folder --dataset somethingv1 --checkpoint_dir /path/for/saving/checkpoints/ --type GST --arch resnet50 --num_segments 8 --beta 2 --alpha 4
• For more details, please type python3 main.py -h

Pretrained Models

• results are reported based on center crop and 1 clip sampling.

Reference

If you find our work useful in your research, please consider citing our paper

@inproceedings{luo2019grouped,
  title={Grouped Spatial-Temporal Aggretation for Efficient Action Recognition},
  author={Luo, Chenxu and Yuille, Alan},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  year={2019}
} 

or

@article{luo2019grouped,
  title={Grouped Spatial-Temporal Aggregation for Efficient Action Recognition},
  author={Luo, Chenxu and Yuille, Alan},
  journal={arXiv preprint arXiv:1909.13130},
  year={2019}
}

Acknowledge

This codebase is build upon TRN-pytorch and TSN-pytorch