Capturing Spatial Interdependence in Image Features : The Counting Grid, an Epitomic Representation for Bags of Features

In recent scene recognition research images or large image regions are often represented as disorganized "bags" of features which can then be analyzed using models originally developed to capture co-variation of word counts in text. However, image feature counts are likely to be constraine...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 37(2015), 12 vom: 21. Dez., Seite 2374-87
1. Verfasser: Perina, Alessandro (VerfasserIn)
Weitere Verfasser: Jojic, Nebojsa
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2015
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM254358950
003 DE-627
005 20231224172212.0
007 cr uuu---uuuuu
008 231224s2015 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2015.2424864  |2 doi 
028 5 2 |a pubmed24n0847.xml 
035 |a (DE-627)NLM254358950 
035 |a (NLM)26539844 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Perina, Alessandro  |e verfasserin  |4 aut 
245 1 0 |a Capturing Spatial Interdependence in Image Features  |b The Counting Grid, an Epitomic Representation for Bags of 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 09.02.2016 
500 |a Date Revised 06.11.2015 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a In recent scene recognition research images or large image regions are often represented as disorganized "bags" of features which can then be analyzed using models originally developed to capture co-variation of word counts in text. However, image feature counts are likely to be constrained in different ways than word counts in text. For example, as a camera pans upwards from a building entrance over its first few floors and then further up into the sky Fig. 1 Fig. 1. Feature counts change slightly as the field of view moves. For example, the abundance of the "car" features is reduced, but the counts of the features found on building facades are increased. The counting grid model accounts for such changes naturally, and it can also account for images of different scenes 
650 4 |a Journal Article 
700 1 |a Jojic, Nebojsa  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 37(2015), 12 vom: 21. Dez., Seite 2374-87  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:37  |g year:2015  |g number:12  |g day:21  |g month:12  |g pages:2374-87 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2015.2424864  |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 37  |j 2015  |e 12  |b 21  |c 12  |h 2374-87