2026-04-14T06:20:42Zhttps://recercat.cat/oai/request

oai:recercat.cat:2072/3550832024-12-13T09:20:14Zcom_2072_228903com_2072_96873com_2072_96852com_2072_2015col_2072_228904

00925njm 22002777a 4500 dc Silveira Jacques Junior, Julio Cezar author Barò Solè, Xavier author Escalera Guerrero, Sergio author Person re-identification has received special attention by the human analysis community in the last few years. To address the challenges in this field, many researchers have proposed different strategies, which basically exploit either cross-view invariant features or cross-view robust metrics. In this work, we propose to exploit a post-ranking approach and combine different feature representations through ranking aggregation. Spatial information, which potentially benefits the person matching, is represented using a 2D body model, from which color and texture information are extracted and combined. We also consider background/foreground information, automatically extracted via Deep Decompositional Network, and the usage of Convolutional Neural Network (CNN) features. To describe the matching between images we use the polynomial feature map, also taking into account local and global information. The Discriminant Context Information Analysis based post-ranking approach is used to improve initial ranking lists. Finally, the Stuart ranking aggregation method is employed to combine complementary ranking lists obtained from different feature representations. Experimental results demonstrated that we improve the state-of-the-art on VIPeR and PRID450s datasets, achieving 67.21% and 75.64% on top-1 rank recognition rate, respectively, as well as obtaining competitive results on CUHK01 dataset. Jacques Junior, J.C.S, Baró, X. & Escalera, S. (2018). Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification. Image and Vision Computing, 79(), 76-85. doi: 10.1016/j.imavis.2018.08.001 0262-8856 10.1016/j.imavis.2018.08.001 http://hdl.handle.net/10609/93179 person re-identification similarity learning feature fusion post-ranking ranking aggregation re-identificació de persones aprenentatge de similituds fusió de característiques post-classificació agregació de classificació re-identificación de personas aprendizaje de similitudes fusión de características post-ranking agregación de clasificación Person identification Identificació de persones Identificación de personas Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification