← Search

Maochen Yang

1 accepted papers

2025

Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting

CVPR 2025poster

Semi-supervised crowd counting is crucial for addressing the high annotation costs of densely populated scenes. Although several methods based on pseudo-labeling have been proposed, it remains challenging to effectively and accurately utilize unlabeled data. In this paper, we propose a novel framewo…