Multilabel Deep Visual-Semantic Embedding

Multilabel Deep Visual-Semantic Embedding

Inspired by the great success from deep convolutional neural networks (CNNs) for single-label visual-semantic embedding, we exploit extending these models for multilabel images. We propose a new learning paradigm for multilabel image classification, in which labels are ranked according to its releva...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 42(2020), 6 vom: 16. Juni, Seite 1530-1536
1. Verfasser: Yeh, Mei-Chen (VerfasserIn)
Weitere Verfasser: Li, Yi-Nan
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2020
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM296112011
003 DE-627
005 20231225085131.0
007 cr uuu---uuuuu
008 231225s2020 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2019.2911065  |2 doi 
028 5 2 |a pubmed24n0987.xml 
035 |a (DE-627)NLM296112011 
035 |a (NLM)30990418 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Yeh, Mei-Chen  |e verfasserin  |4 aut 
245 1 0 |a Multilabel Deep Visual-Semantic Embedding 
264 1 |c 2020 
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 03.09.2020 
500 |a Date Revised 03.09.2020 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Inspired by the great success from deep convolutional neural networks (CNNs) for single-label visual-semantic embedding, we exploit extending these models for multilabel images. We propose a new learning paradigm for multilabel image classification, in which labels are ranked according to its relevance to the input image. In contrast to conventional CNN models that learn a latent vector representation (i.e., the image embedding vector), the developed visual model learns a mapping (i.e., a transformation matrix) from an image in an attempt to differentiate between its relevant and irrelevant labels. Despite the conceptual simplicity of our approach, the proposed model achieves state-of-the-art results on three public benchmark datasets 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Li, Yi-Nan  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 42(2020), 6 vom: 16. Juni, Seite 1530-1536  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:42  |g year:2020  |g number:6  |g day:16  |g month:06  |g pages:1530-1536 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2019.2911065  |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 42  |j 2020  |e 6  |b 16  |c 06  |h 1530-1536