no code implementations • 26 Nov 2023 • Yuehai Chen
In the proposed module, the data-driven mechanism can effectively extract the feature representations of dynamic human-human interactions in the scene and calculate the corresponding weights to represent the importance of different interactions.
no code implementations • 8 Nov 2023 • Yuehai Chen
Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations.
no code implementations • 29 Jul 2023 • Yuehai Chen, Jing Yang, Badong Chen, Hua Gang, Shaoyi Du
To improve the robustness to annotation displacement, we design an effective transport cost function based on GGD.
no code implementations • 21 Jun 2022 • Yuehai Chen, Jing Yang, Badong Chen, Shaoyi Du
Thus, CNN could locate and estimate crowds accurately in low-density regions, while it is hard to properly perceive the densities in high-density regions.
no code implementations • 23 Jun 2021 • Yuehai Chen, Jing Yang, Dong Zhang, Kun Zhang, Badong Chen, Shaoyi Du
More specifically, we scan the whole input images and its priority maps in the form of column vector to obtain a relevance matrix estimating their similarity.