Object detection with convolutional context features

Abstract

A novel extension to Hızlı B-ESA object detection algorithm is proposed in order to learn convolutional context features for determining boundaries of objects better. For input images, the hypothesis windows and their context around those windows are learned through convolutional layers as two pa­rallel networks. The resulting object… (More)
DOI: 10.1109/SIU.2017.7960502

Topics

Figures and Tables

Sorry, we couldn't extract any figures or tables for this paper.

Slides referencing similar topics