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...
Main Authors: | , , , |
---|---|
其他作者: | |
格式: | Journal Article |
语言: | English |
出版: |
2022
|
主题: | |
在线阅读: | https://hdl.handle.net/10356/160520 |