A self-training approach for point-supervised object detection and counting in crowds

In this article, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the center points and sizes of crowded objects. Specifically, during training, we uti...

全面介绍

书目详细资料
Main Authors: Wang, Yi, Hou, Junhui, Hou, Xinyu, Chau, Lap-Pui
其他作者: School of Electrical and Electronic Engineering
格式: Journal Article
语言:English
出版: 2022
主题:
在线阅读:https://hdl.handle.net/10356/160520