Publications

Semi-supervised Crowd Counting with Spatial Temporal Consistency and Pseudo-label Filter

Published in IEEE TCSVT, 2023

The performance of semi-supervised crowd counting (SSCC) can be significantly improved by reducing the over-fitting of the incorrect pseudo labels. This paper proposed a novel spatial-temporal consistency framework, named STC-Crowd.

Multi-scale context aggregation network with attention-guided for crowd counting

Published in 15-th IEEE International Conference on Signal Processing, 2020

This paper is about the number 2. The number 3 is left for future work.

Xin Wang

Publications

Semi-supervised Crowd Counting with Spatial Temporal Consistency and Pseudo-label Filter

Multi-scale context aggregation network with attention-guided for crowd counting