Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312733587> ?p ?o ?g. }
- W4312733587 endingPage "35" @default.
- W4312733587 startingPage "19" @default.
- W4312733587 abstract "Fashion designs are rich in visual details associated with various visual attributes at both global and local levels. As a result, effective modeling and analyzing fashion requires fine-grained representations for individual attributes. In this work, we present a deep learning based online clustering method to jointly learn fine-grained fashion representations for all attributes at both instance and cluster level, where the attribute-specific cluster centers are online estimated. Based on the similarity between fine-grained representations and cluster centers, attribute-specific embedding spaces are further segmented into class-specific embedding spaces for fine-grained fashion retrieval. To better regulate the learning process, we design a three-stage learning scheme, to progressively incorporate different supervisions at both instance and cluster level, from both original and augmented data, and with ground-truth and pseudo labels. Experiments on FashionAI and DARN datasets in the retrieval task demonstrated the efficacy of our method compared with competing baselines." @default.
- W4312733587 created "2023-01-05" @default.
- W4312733587 creator A5010965630 @default.
- W4312733587 creator A5021319176 @default.
- W4312733587 creator A5021739840 @default.
- W4312733587 creator A5050626705 @default.
- W4312733587 creator A5079341536 @default.
- W4312733587 date "2022-01-01" @default.
- W4312733587 modified "2023-09-26" @default.
- W4312733587 title "Fine-Grained Fashion Representation Learning by Online Deep Clustering" @default.
- W4312733587 cites W1946323491 @default.
- W4312733587 cites W2027731328 @default.
- W4312733587 cites W2170881581 @default.
- W4312733587 cites W2200092826 @default.
- W4312733587 cites W2221507685 @default.
- W4312733587 cites W2321533354 @default.
- W4312733587 cites W2471768434 @default.
- W4312733587 cites W2735001949 @default.
- W4312733587 cites W2795117763 @default.
- W4312733587 cites W2798951647 @default.
- W4312733587 cites W2798991696 @default.
- W4312733587 cites W2802650881 @default.
- W4312733587 cites W2883725317 @default.
- W4312733587 cites W2892607309 @default.
- W4312733587 cites W2963258075 @default.
- W4312733587 cites W2963367015 @default.
- W4312733587 cites W2963857660 @default.
- W4312733587 cites W2964211610 @default.
- W4312733587 cites W2970127347 @default.
- W4312733587 cites W2981952041 @default.
- W4312733587 cites W2988281744 @default.
- W4312733587 cites W2998315347 @default.
- W4312733587 cites W3004246805 @default.
- W4312733587 cites W3034576826 @default.
- W4312733587 cites W3142806976 @default.
- W4312733587 cites W3171007011 @default.
- W4312733587 cites W3199485894 @default.
- W4312733587 cites W3215912690 @default.
- W4312733587 doi "https://doi.org/10.1007/978-3-031-19812-0_2" @default.
- W4312733587 hasPublicationYear "2022" @default.
- W4312733587 type Work @default.
- W4312733587 citedByCount "1" @default.
- W4312733587 countsByYear W43127335872023 @default.
- W4312733587 crossrefType "book-chapter" @default.
- W4312733587 hasAuthorship W4312733587A5010965630 @default.
- W4312733587 hasAuthorship W4312733587A5021319176 @default.
- W4312733587 hasAuthorship W4312733587A5021739840 @default.
- W4312733587 hasAuthorship W4312733587A5050626705 @default.
- W4312733587 hasAuthorship W4312733587A5079341536 @default.
- W4312733587 hasConcept C103278499 @default.
- W4312733587 hasConcept C108583219 @default.
- W4312733587 hasConcept C111919701 @default.
- W4312733587 hasConcept C115961682 @default.
- W4312733587 hasConcept C119857082 @default.
- W4312733587 hasConcept C134306372 @default.
- W4312733587 hasConcept C146849305 @default.
- W4312733587 hasConcept C154945302 @default.
- W4312733587 hasConcept C162324750 @default.
- W4312733587 hasConcept C164866538 @default.
- W4312733587 hasConcept C17744445 @default.
- W4312733587 hasConcept C187736073 @default.
- W4312733587 hasConcept C199360897 @default.
- W4312733587 hasConcept C199539241 @default.
- W4312733587 hasConcept C23123220 @default.
- W4312733587 hasConcept C2776359362 @default.
- W4312733587 hasConcept C2777212361 @default.
- W4312733587 hasConcept C2780451532 @default.
- W4312733587 hasConcept C33923547 @default.
- W4312733587 hasConcept C41008148 @default.
- W4312733587 hasConcept C41608201 @default.
- W4312733587 hasConcept C59404180 @default.
- W4312733587 hasConcept C73555534 @default.
- W4312733587 hasConcept C77618280 @default.
- W4312733587 hasConcept C94625758 @default.
- W4312733587 hasConcept C98045186 @default.
- W4312733587 hasConceptScore W4312733587C103278499 @default.
- W4312733587 hasConceptScore W4312733587C108583219 @default.
- W4312733587 hasConceptScore W4312733587C111919701 @default.
- W4312733587 hasConceptScore W4312733587C115961682 @default.
- W4312733587 hasConceptScore W4312733587C119857082 @default.
- W4312733587 hasConceptScore W4312733587C134306372 @default.
- W4312733587 hasConceptScore W4312733587C146849305 @default.
- W4312733587 hasConceptScore W4312733587C154945302 @default.
- W4312733587 hasConceptScore W4312733587C162324750 @default.
- W4312733587 hasConceptScore W4312733587C164866538 @default.
- W4312733587 hasConceptScore W4312733587C17744445 @default.
- W4312733587 hasConceptScore W4312733587C187736073 @default.
- W4312733587 hasConceptScore W4312733587C199360897 @default.
- W4312733587 hasConceptScore W4312733587C199539241 @default.
- W4312733587 hasConceptScore W4312733587C23123220 @default.
- W4312733587 hasConceptScore W4312733587C2776359362 @default.
- W4312733587 hasConceptScore W4312733587C2777212361 @default.
- W4312733587 hasConceptScore W4312733587C2780451532 @default.
- W4312733587 hasConceptScore W4312733587C33923547 @default.
- W4312733587 hasConceptScore W4312733587C41008148 @default.
- W4312733587 hasConceptScore W4312733587C41608201 @default.
- W4312733587 hasConceptScore W4312733587C59404180 @default.
- W4312733587 hasConceptScore W4312733587C73555534 @default.