IVAC-P²L: Leveraging Irregular Repetition Priors for Improving Video Action Counting

Hang Wang^1,2 | Zhi-Qi Cheng³ | Youtian Du¹ | Lei Zhang^2
1Xi'an Jiaotong University, ²The Hong Kong Polytechnic University, ³Carnegie Mellon University

Preparing Datasets

We train on the training set of the RepCount-A dataset, and test on the testing set of the RepCount-A dataset, the validation sets of the UCFRep and Countix datasets.

Download datasets: RepCount-A, UCFRep, Countix

Train

on the training set of the RepCount-A dataset

python train.py

Test

on the testing set of the RepCount-A dataset

python test.py

Pre-trained Checkpoint on RepCount-A

We also provide a pre-trained model for RepCount-A, which can be downloaded from this Google Drive link.

Acknowledgement

Thanks for works of TransRAC. Our code is based on these implementations.

Citation

@article{wang2024ivac,
  title={IVAC-P2L: Enhancing Video Action Counting through Irregular Repetition Priors},
  author={Wang, Hang and Cheng, Zhi-Qi and Du, Youtian and Zhang, Lei},
  journal={arXiv preprint arXiv:2403.11959},
  year={2024}
}

Contact

If you have any questions, please feel free to contact: [email protected]

statistics