By Luxuan Li, Tao Kong, Fuchun Sun, Huaping Liu.
Pytorch implementation of the activity proposal and detection model described in our ICONIP 2019 oral paper "Deep Point-wise Prediction for Action Temporal Proposal".
We present a simple and effective method for temporal action proposal generation, named Deep Point-wise Prediction (DPP). DPP simultaneously predicts the action existing possibility and the corresponding temporal locations, without the utilization of any handcrafted sliding window or grouping. The whole system is end-to-end trained with joint loss of temporal action proposal classification and location prediction.
We are still working on it and will release the codes soon.
If you find our work useful, please use the following bibtex to cite our work:
@inproceedings{li2019dpp,
author = {Luxuan Li, Tao Kong, Fuchun Sun and Huaping Liu},
title = {Deep Point-wise Prediction for Action TemporalProposal},
booktitle = {International Conference on Neural Information Processing (ICONIP)},
year = {2019}
}