Learning to relate images

A fundamental operation in many vision tasks, including motion understanding, stereopsis, visual odometry, or invariant recognition, is establishing correspondences between images or between images and data from other modalities. Recently, there has been increasing interest in learning to infer corr...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 35(2013), 8 vom: 20. Aug., Seite 1829-46
1. Verfasser: Memisevic, Roland (VerfasserIn)
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2013
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't Review
LEADER 01000naa a22002652 4500
001 NLM228521246
003 DE-627
005 20231224080118.0
007 cr uuu---uuuuu
008 231224s2013 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2013.53  |2 doi 
028 5 2 |a pubmed24n0761.xml 
035 |a (DE-627)NLM228521246 
035 |a (NLM)23787339 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Memisevic, Roland  |e verfasserin  |4 aut 
245 1 0 |a Learning to relate images 
264 1 |c 2013 
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 17.02.2014 
500 |a Date Revised 21.06.2013 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a A fundamental operation in many vision tasks, including motion understanding, stereopsis, visual odometry, or invariant recognition, is establishing correspondences between images or between images and data from other modalities. Recently, there has been increasing interest in learning to infer correspondences from data using relational, spatiotemporal, and bilinear variants of deep learning methods. These methods use multiplicative interactions between pixels or between features to represent correlation patterns across multiple images. In this paper, we review the recent work on relational feature learning, and we provide an analysis of the role that multiplicative interactions play in learning to encode relations. We also discuss how square-pooling and complex cell models can be viewed as a way to represent multiplicative interactions and thereby as a way to encode relations 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
650 4 |a Review 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 35(2013), 8 vom: 20. Aug., Seite 1829-46  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:35  |g year:2013  |g number:8  |g day:20  |g month:08  |g pages:1829-46 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2013.53  |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 35  |j 2013  |e 8  |b 20  |c 08  |h 1829-46