Filters








1 Hit in 3.1 sec

Deep Learning Techniques for Visual Counting [article]

Luca Ciampi
2022 arXiv   pre-print
In this dissertation, we investigated and enhanced Deep Learning (DL) techniques for counting objects, like pedestrians, cells or vehicles, in still images or video frames.  ...  counting strategy in a weakly labeled data scenario, i.e., in the presence of non-negligible disagreement between multiple annotators.  ...  For example, [97] proposed SAU-Net, an extension of the U-Net segmentation network [191] with a Self-Attention module for counting by density regression.  ... 
arXiv:2206.03033v2 fatcat:johyxd4slrcjlad36qwwbk7l3q