Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100847621> ?p ?o ?g. }
- W3100847621 endingPage "344" @default.
- W3100847621 startingPage "332" @default.
- W3100847621 abstract "In this paper, we propose an adversarial multi-label variational hashing (AMVH) method to learn compact binary codes for efficient image retrieval. Unlike most existing deep hashing methods which only learn binary codes from specific real samples, our AMVH learns hash functions from both synthetic and real data which make our model effective for unseen data. Specifically, we design an end-to-end deep hashing framework which consists of a generator network and a discriminator-hashing network by enforcing simultaneous adversarial learning and discriminative binary codes learning to learn compact binary codes. The discriminator-hashing network learns binary codes by optimizing a multi-label discriminative criterion and minimizing the quantization loss between binary codes and real-value codes. The generator network is learned so that latent representations can be sampled in a probabilistic manner and used to generate new synthetic training sample for the discriminator-hashing network. Experimental results on several benchmark datasets show the efficacy of the proposed approach." @default.
- W3100847621 created "2020-11-23" @default.
- W3100847621 creator A5019615508 @default.
- W3100847621 creator A5020313082 @default.
- W3100847621 creator A5090079801 @default.
- W3100847621 date "2021-01-01" @default.
- W3100847621 modified "2023-10-17" @default.
- W3100847621 title "Adversarial Multi-Label Variational Hashing" @default.
- W3100847621 cites W1705126064 @default.
- W3100847621 cites W1910300841 @default.
- W3100847621 cites W1939575207 @default.
- W3100847621 cites W1985417744 @default.
- W3100847621 cites W1987566020 @default.
- W3100847621 cites W2007972815 @default.
- W3100847621 cites W2013808584 @default.
- W3100847621 cites W2029205712 @default.
- W3100847621 cites W2066761620 @default.
- W3100847621 cites W2074668987 @default.
- W3100847621 cites W2084363474 @default.
- W3100847621 cites W2089632823 @default.
- W3100847621 cites W2124509324 @default.
- W3100847621 cites W2126210882 @default.
- W3100847621 cites W2145065594 @default.
- W3100847621 cites W2155803963 @default.
- W3100847621 cites W2171790913 @default.
- W3100847621 cites W2197560310 @default.
- W3100847621 cites W2388114291 @default.
- W3100847621 cites W2435696002 @default.
- W3100847621 cites W2464915613 @default.
- W3100847621 cites W2594105920 @default.
- W3100847621 cites W2733548594 @default.
- W3100847621 cites W2738649458 @default.
- W3100847621 cites W2739130108 @default.
- W3100847621 cites W2739565366 @default.
- W3100847621 cites W2752674409 @default.
- W3100847621 cites W2798956329 @default.
- W3100847621 cites W2896050315 @default.
- W3100847621 cites W2963709863 @default.
- W3100847621 cites W2964076257 @default.
- W3100847621 cites W3103722964 @default.
- W3100847621 doi "https://doi.org/10.1109/tip.2020.3036735" @default.
- W3100847621 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33186108" @default.
- W3100847621 hasPublicationYear "2021" @default.
- W3100847621 type Work @default.
- W3100847621 sameAs 3100847621 @default.
- W3100847621 citedByCount "12" @default.
- W3100847621 countsByYear W31008476212020 @default.
- W3100847621 countsByYear W31008476212021 @default.
- W3100847621 countsByYear W31008476212022 @default.
- W3100847621 countsByYear W31008476212023 @default.
- W3100847621 crossrefType "journal-article" @default.
- W3100847621 hasAuthorship W3100847621A5019615508 @default.
- W3100847621 hasAuthorship W3100847621A5020313082 @default.
- W3100847621 hasAuthorship W3100847621A5090079801 @default.
- W3100847621 hasConcept C11413529 @default.
- W3100847621 hasConcept C122907437 @default.
- W3100847621 hasConcept C133667856 @default.
- W3100847621 hasConcept C138111711 @default.
- W3100847621 hasConcept C153180895 @default.
- W3100847621 hasConcept C154945302 @default.
- W3100847621 hasConcept C2779803651 @default.
- W3100847621 hasConcept C28855332 @default.
- W3100847621 hasConcept C33923547 @default.
- W3100847621 hasConcept C38652104 @default.
- W3100847621 hasConcept C41008148 @default.
- W3100847621 hasConcept C48372109 @default.
- W3100847621 hasConcept C63435697 @default.
- W3100847621 hasConcept C67388219 @default.
- W3100847621 hasConcept C76155785 @default.
- W3100847621 hasConcept C80444323 @default.
- W3100847621 hasConcept C94375191 @default.
- W3100847621 hasConcept C94915269 @default.
- W3100847621 hasConcept C97931131 @default.
- W3100847621 hasConcept C99138194 @default.
- W3100847621 hasConceptScore W3100847621C11413529 @default.
- W3100847621 hasConceptScore W3100847621C122907437 @default.
- W3100847621 hasConceptScore W3100847621C133667856 @default.
- W3100847621 hasConceptScore W3100847621C138111711 @default.
- W3100847621 hasConceptScore W3100847621C153180895 @default.
- W3100847621 hasConceptScore W3100847621C154945302 @default.
- W3100847621 hasConceptScore W3100847621C2779803651 @default.
- W3100847621 hasConceptScore W3100847621C28855332 @default.
- W3100847621 hasConceptScore W3100847621C33923547 @default.
- W3100847621 hasConceptScore W3100847621C38652104 @default.
- W3100847621 hasConceptScore W3100847621C41008148 @default.
- W3100847621 hasConceptScore W3100847621C48372109 @default.
- W3100847621 hasConceptScore W3100847621C63435697 @default.
- W3100847621 hasConceptScore W3100847621C67388219 @default.
- W3100847621 hasConceptScore W3100847621C76155785 @default.
- W3100847621 hasConceptScore W3100847621C80444323 @default.
- W3100847621 hasConceptScore W3100847621C94375191 @default.
- W3100847621 hasConceptScore W3100847621C94915269 @default.
- W3100847621 hasConceptScore W3100847621C97931131 @default.
- W3100847621 hasConceptScore W3100847621C99138194 @default.
- W3100847621 hasFunder F4320321001 @default.
- W3100847621 hasFunder F4320322392 @default.
- W3100847621 hasFunder F4320335803 @default.
- W3100847621 hasLocation W31008476211 @default.