Optimizing Video Object Detection via a Scale-Time Lattice

CVPR, pp. 7814-7823, 2018.

Cited by: 50|Views109
EI

Abstract:

High-performance object detection relies on expensive convolutional networks to compute features, often leading to significant challenges in applications, e.g. those that require detecting objects from video streams in real time. The key to this problem is to trade accuracy for efficiency in an effective way, i.e. reducing the computing c...More

Code:

Data:

Your rating :
0

 

Tags
Comments