|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM275310752 |
| 003 |
DE-627 |
| 005 |
20231225005405.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2017 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2017.2745106
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n0917.xml
|
| 035 |
|
|
|a (DE-627)NLM275310752
|
| 035 |
|
|
|a (NLM)28858796
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Ke Li
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval
|
| 264 |
|
1 |
|c 2017
|
| 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 11.12.2018
|
| 500 |
|
|
|a Date Revised 11.12.2018
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a We study the problem of fine-grained sketch-based image retrieval. By performing instance-level (rather than category-level) retrieval, it embodies a timely and practical application, particularly with the ubiquitous availability of touchscreens. Three factors contribute to the challenging nature of the problem: 1) free-hand sketches are inherently abstract and iconic, making visual comparisons with photos difficult; 2) sketches and photos are in two different visual domains, i.e., black and white lines versus color pixels; and 3) fine-grained distinctions are especially challenging when executed across domain and abstraction-level. To address these challenges, we propose to bridge the image-sketch gap both at the high level via parts and attributes, as well as at the low level via introducing a new domain alignment method. More specifically, first, we contribute a data set with 304 photos and 912 sketches, where each sketch and image is annotated with its semantic parts and associated part-level attributes. With the help of this data set, second, we investigate how strongly supervised deformable part-based models can be learned that subsequently enable automatic detection of part-level attributes, and provide pose-aligned sketch-image comparisons. To reduce the sketch-image gap when comparing low-level features, third, we also propose a novel method for instance-level domain-alignment that exploits both subspace and instance-level cues to better align the domains. Finally, fourth, these are combined in a matching framework integrating aligned low-level features, mid-level geometric structure, and high-level semantic attributes. Extensive experiments conducted on our new data set demonstrate effectiveness of the proposed method
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Kaiyue Pang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yi-Zhe Song
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hospedales, Timothy M
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Tao Xiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Honggang Zhang
|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 26(2017), 12 vom: 20. Dez., Seite 5908-5921
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:26
|g year:2017
|g number:12
|g day:20
|g month:12
|g pages:5908-5921
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2017.2745106
|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 26
|j 2017
|e 12
|b 20
|c 12
|h 5908-5921
|