Towards High Performance Video Object Detection for Mobiles

arXiv: Computer Vision and Pattern Recognition, Volume abs/1804.05830, 2018.

Cited by: 11|Bibtex|Views81
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Despite the recent success of video object detection on Desktop GPUs, its architecture is still far too heavy for mobiles. It is also unclear whether the key principles of sparse feature propagation and multi-frame feature aggregation apply at very limited computational resources. In this paper, we present a light weight network architect...More

Code:

Data:

Your rating :
0

 

Tags
Comments