Using language to learn structured appearance models for image annotation

Using language to learn structured appearance models for image annotation

Given an unstructured collection of captioned images of cluttered scenes featuring a variety of objects, our goal is to simultaneously learn the names and appearances of the objects. Only a small fraction of local features within any given image are associated with a particular caption word, and cap...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1998. - 32(2010), 1 vom: 08. Jan., Seite 148-64
Auteur principal: Jamieson, Michael (Auteur)
Autres auteurs: Fazly, Afsaneh, Stevenson, Suzanne, Dickinson, Sven, Wachsmuth, Sven
Format: Article en ligne
Langue:English
Publié: 2010
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000caa a22002652 4500
001 NLM192953680
003 DE-627
005 20250211004843.0
007 cr uuu---uuuuu
008 231223s2010 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2008.283  |2 doi 
028 5 2 |a pubmed25n0643.xml 
035 |a (DE-627)NLM192953680 
035 |a (NLM)19926905 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Jamieson, Michael  |e verfasserin  |4 aut 
245 1 0 |a Using language to learn structured appearance models for image annotation 
264 1 |c 2010 
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 25.01.2010 
500 |a Date Revised 20.11.2009 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Given an unstructured collection of captioned images of cluttered scenes featuring a variety of objects, our goal is to simultaneously learn the names and appearances of the objects. Only a small fraction of local features within any given image are associated with a particular caption word, and captions may contain irrelevant words not associated with any image object. We propose a novel algorithm that uses the repetition of feature neighborhoods across training images and a measure of correspondence with caption words to learn meaningful feature configurations (representing named objects). We also introduce a graph-based appearance model that captures some of the structure of an object by encoding the spatial relationships among the local visual features. In an iterative procedure, we use language (the words) to drive a perceptual grouping process that assembles an appearance model for a named object. Results of applying our method to three data sets in a variety of conditions demonstrate that, from complex, cluttered, real-world scenes with noisy captions, we can learn both the names and appearances of objects, resulting in a set of models invariant to translation, scale, orientation, occlusion, and minor changes in viewpoint or articulation. These named models, in turn, are used to automatically annotate new, uncaptioned images, thereby facilitating keyword-based image retrieval 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Fazly, Afsaneh  |e verfasserin  |4 aut 
700 1 |a Stevenson, Suzanne  |e verfasserin  |4 aut 
700 1 |a Dickinson, Sven  |e verfasserin  |4 aut 
700 1 |a Wachsmuth, Sven  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1998  |g 32(2010), 1 vom: 08. Jan., Seite 148-64  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:32  |g year:2010  |g number:1  |g day:08  |g month:01  |g pages:148-64 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2008.283  |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 32  |j 2010  |e 1  |b 08  |c 01  |h 148-64