DMRNet++: Learning Discriminative Features with Decoupled Networks and Enriched Pairs for One-Step Person Searchhcc

Person search aims at localizing and recognizing query persons from raw video frames, which is a combination of two sub-tasks, i.e., pedestrian detection and person re-identification. The dominant fashion is termed as the one-step person search that jointly optimizes detection and identification in...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2022, p.1-18
Hauptverfasser:	Han, Chuchu, Zheng, Zhedong, Su, Kai, Yu, Dongdong, Yuan, Zehuan, Gao, Changxin, Sang, Nong, Yang, Yi
Format:	Artikel
Sprache:	eng
Schlagworte:	Detectors Encoding Feature extraction Noise measurement Object Detection Person Re-identification Person Search Representation learning Semi-Supervised Learning Semisupervised learning Task analysis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!