Crowd Counting via Cross stage Refinement Networks
IEEE Transactions on Image Processing, 2020.
Crowd counting is challenging due to unconstrained imaging factors, e.g., background clutters, non-uniform distribution of people, large scale and perspective variations. Dealing with these problems using deep neural networks requires rich prior knowledge and multi-scale contextual representations. In this paper, we propose a Cross-stage ...More
Full Text (Upload PDF)
PPT (Upload PPT)