ML Anthology

Towards High Performance Video Object Detection

Xizhou Zhu, Jifeng Dai, Lu Yuan, Yichen Wei
CVPR 2018
doi:10.1109/CVPR.2018.00753 /cvpr/2018/zhu2018cvpr-high/

Abstract

There has been significant progresses for image object detection recently. Nevertheless, video object detection has received little attention, although it is more challenging and more important in practical scenarios. Built upon the recent works, this work proposes a unified viewpoint based on the principle of multi-frame end-to-end learning of features and cross-frame motion. Our approach extends prior works with three new techniques and steadily pushes forward the performance envelope (speed-accuracy tradeoff), towards high performance video object detection.

PDF CVPR Semantic Scholar

Cite

Text

Zhu et al. "Towards High Performance Video Object Detection." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00753

Markdown

[Zhu et al. "Towards High Performance Video Object Detection." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/zhu2018cvpr-high/) doi:10.1109/CVPR.2018.00753

BibTeX

@inproceedings{zhu2018cvpr-high,
  title     = {{Towards High Performance Video Object Detection}},
  author    = {Zhu, Xizhou and Dai, Jifeng and Yuan, Lu and Wei, Yichen},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00753},
  url       = {https://mlanthology.org/cvpr/2018/zhu2018cvpr-high/}
}