Page
%P
-
Chapter and Conference Paper
Grou** and Recurrent Feature Encoding Based Multi-task Learning for Pedestrian Attribute Recognition
Pedestrian attribute recognition (PAR) in surveillance is to predict pedestrian visual features (somatotype, wearing style, etc.). Existing methods usually elaborately design complex multi-label deep neural ne...
-
Chapter and Conference Paper
An Advanced Least Squares Twin Multi-class Classification Support Vector Machine for Few-Shot Classification
In classification tasks, deep learning methods yield high performance. However, owing to lack of enough annotated data, deep learning methods often underperformed. Therefore, we propose an advance version of l...