|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM339425253 |
| 003 |
DE-627 |
| 005 |
20231226002851.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2022.3165376
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1131.xml
|
| 035 |
|
|
|a (DE-627)NLM339425253
|
| 035 |
|
|
|a (NLM)35412982
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Liang, Chao
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Rethinking the Competition Between Detection and ReID in Multiobject Tracking
|
| 264 |
|
1 |
|c 2022
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 26.04.2022
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a 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 because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a self-relation and cross-relation design so that to impel each branch to better learn task-dependent representations. The proposed model aims to alleviate the deleterious tasks competition, meanwhile improve the cooperation between detection and ReID. Furthermore, we introduce a scale-aware attention network (SAAN) that prevents semantic level misalignment to improve the association capability of ID embeddings. By integrating the two delicately designed networks into a one-shot online MOT system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The complete code has been released at https://github.com/JudasDie/SOTS
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhang, Zhipeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhou, Xue
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Bing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhu, Shuyuan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hu, Weiming
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 31(2022) vom: 12., Seite 3182-3196
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:31
|g year:2022
|g day:12
|g pages:3182-3196
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2022.3165376
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 31
|j 2022
|b 12
|h 3182-3196
|