|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM318256088 |
| 003 |
DE-627 |
| 005 |
20231225164954.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2021 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2020.3037518
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1060.xml
|
| 035 |
|
|
|a (DE-627)NLM318256088
|
| 035 |
|
|
|a (NLM)33259298
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Yuan, Di
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Self-Supervised Deep Correlation Tracking
|
| 264 |
|
1 |
|c 2021
|
| 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 10.12.2020
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a The training of a feature extraction network typically requires abundant manually annotated training samples, making this a time-consuming and costly process. Accordingly, we propose an effective self-supervised learning-based tracker in a deep correlation framework (named: self-SDCT). Motivated by the forward-backward tracking consistency of a robust tracker, we propose a multi-cycle consistency loss as self-supervised information for learning feature extraction network from adjacent video frames. At the training stage, we generate pseudo-labels of consecutive video frames by forward-backward prediction under a Siamese correlation tracking framework and utilize the proposed multi-cycle consistency loss to learn a feature extraction network. Furthermore, we propose a similarity dropout strategy to enable some low-quality training sample pairs to be dropped and also adopt a cycle trajectory consistency loss in each sample pair to improve the training loss function. At the tracking stage, we employ the pre-trained feature extraction network to extract features and utilize a Siamese correlation tracking framework to locate the target using forward tracking alone. Extensive experimental results indicate that the proposed self-supervised deep correlation tracker (self-SDCT) achieves competitive tracking performance contrasted to state-of-the-art supervised and unsupervised tracking methods on standard evaluation benchmarks
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Chang, Xiaojun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Huang, Po-Yao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Qiao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a He, Zhenyu
|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 30(2021) vom: 01., Seite 976-985
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:30
|g year:2021
|g day:01
|g pages:976-985
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2020.3037518
|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 30
|j 2021
|b 01
|h 976-985
|