Rethinking the Competition Between Detection and ReID in Multiobject Tracking

• Published in: IEEE transactions on image processing Vol. 31; pp. 3182 - 3196
• Main Authors: Liang, Chao, Zhang, Zhipeng, Zhou, Xue, Li, Bing, Zhu, Shuyuan, Hu, Weiming
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bells; Competition; Computational modeling; Detectors; Feature extraction; ID embedding; Misalignment; Multiobject tracking; Multiple target tracking; Object detection; one-shot; reciprocal representation learning; Representations; scale-aware attention; Semantics; Target tracking; Task analysis

Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked beca...