This repo contains the Scene Separation and Data Selection Algorithm used for real-time video stream analysis.
This algorithm is a work featured in IJCAI 2022 workshop Spatio-Temporal Reasoning and Learning.
Go to /slides
for the oral presentation slides, go to arXiv for the paper.
Watch our STRL2022 keynote presentation on YouTube or Bilibili.
- add the previously implemented code to this repo
- refine 2SDS architecture
- consider a graph neural network approach
If you find this work useful, please cite our paper:
@misc{2sds2022,
title={Scene Separation & Data Selection: Temporal Segmentation Algorithm for Real-time Video Stream Analysis},
author={Yuelin Xin and Zihan Zhou and Yuxuan Xia},
year={2022},
eprint={2308.00210},
archivePrefix={arXiv},
primaryClass={cs.CV}
}