A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2021.3055632
Abstract: 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… read more here.
Keywords: point supervised; self training; training approach; point ... See more keywords