|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM24641572X |
| 003 |
DE-627 |
| 005 |
20231224143020.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231224s2015 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2015.2403231
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n0821.xml
|
| 035 |
|
|
|a (DE-627)NLM24641572X
|
| 035 |
|
|
|a (NLM)25700445
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Li Wang
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Video tracking using learned hierarchical features
|
| 264 |
|
1 |
|c 2015
|
| 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 Completed 21.04.2015
|
| 500 |
|
|
|a Date Revised 10.04.2015
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a In this paper, we propose an approach to learn hierarchical features for visual object tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video sequences. The hierarchical features are learned via a two-layer convolutional neural network. Embedding the temporal slowness constraint in the stacked architecture makes the learned features robust to complicated motion transformations, which is important for visual object tracking. Then, given a target video sequence, we propose a domain adaptation module to online adapt the pre-learned features according to the specific target object. The adaptation is conducted in both layers of the deep feature learning module so as to include appearance information of the specific target object. As a result, the learned hierarchical features can be robust to both complicated motion transformations and appearance changes of target objects. We integrate our feature learning algorithm into three tracking methods. Experimental results demonstrate that significant improvement can be achieved using our learned hierarchical features, especially on video sequences with complicated motion transformations
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, Non-U.S. Gov't
|
| 700 |
1 |
|
|a Ting Liu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Gang Wang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Kap Luk Chan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Qingxiong Yang
|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 24(2015), 4 vom: 09. Apr., Seite 1424-35
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:24
|g year:2015
|g number:4
|g day:09
|g month:04
|g pages:1424-35
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2015.2403231
|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 24
|j 2015
|e 4
|b 09
|c 04
|h 1424-35
|