Multi-feature sparse similar representation for person identification
作者：
Highlights：
• The discriminative body appearance feature is designed by reconstructing different spatial features with their spatial correlation and jointly combining all spatial representations.
• l1-norm weighted distance is adopted in our multi-feature representation model, which is more robust than the conventional l2-norm regularization.
• Competitive results have been achieved by our proposed model in addressing the multi-feature person identification problem.
摘要
•The discriminative body appearance feature is designed by reconstructing different spatial features with their spatial correlation and jointly combining all spatial representations.•l1-norm weighted distance is adopted in our multi-feature representation model, which is more robust than the conventional l2-norm regularization.•Competitive results have been achieved by our proposed model in addressing the multi-feature person identification problem.
论文关键词：Multi-feature,Person identification,Sparse representation
论文评审过程：Received 31 October 2020, Revised 14 July 2022, Accepted 20 July 2022, Available online 21 July 2022, Version of Record 29 July 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108916
