Matches in SemOpenAlex for { <https://semopenalex.org/work/W2573350151> ?p ?o ?g. }
- W2573350151 abstract "Learning-based binary hashing has become a powerful paradigm for fast search and retrieval in massive databases. However, due to the requirement of discrete outputs for the hash functions, learning such functions is known to be very challenging. In addition, the objective functions adopted by existing hashing techniques are mostly chosen heuristically. In this paper, we propose a novel generative approach to learn hash functions through Minimum Description Length principle such that the learned hash codes maximally compress the dataset and can also be used to regenerate the inputs. We also develop an efficient learning algorithm based on the stochastic distributional gradient, which avoids the notorious difficulty caused by binary output constraints, to jointly optimize the parameters of the hash function and the associated generative model. Extensive experiments on a variety of large-scale datasets show that the proposed method achieves better retrieval results than the existing state-of-the-art methods." @default.
- W2573350151 created "2017-01-26" @default.
- W2573350151 creator A5007775697 @default.
- W2573350151 creator A5018301052 @default.
- W2573350151 creator A5030589527 @default.
- W2573350151 creator A5071683073 @default.
- W2573350151 creator A5086484914 @default.
- W2573350151 date "2017-01-11" @default.
- W2573350151 modified "2023-10-11" @default.
- W2573350151 title "Stochastic Generative Hashing" @default.
- W2573350151 cites W138284169 @default.
- W2573350151 cites W1502916507 @default.
- W2573350151 cites W1522301498 @default.
- W2573350151 cites W1852777783 @default.
- W2573350151 cites W1893754589 @default.
- W2573350151 cites W1977182282 @default.
- W2573350151 cites W1983334819 @default.
- W2573350151 cites W1992208280 @default.
- W2573350151 cites W1996936615 @default.
- W2573350151 cites W2029205712 @default.
- W2573350151 cites W2044195942 @default.
- W2573350151 cites W2047229728 @default.
- W2573350151 cites W2053546771 @default.
- W2573350151 cites W2084363474 @default.
- W2573350151 cites W2095304671 @default.
- W2573350151 cites W2102409316 @default.
- W2573350151 cites W2242818861 @default.
- W2573350151 cites W2251864938 @default.
- W2573350151 cites W2259167532 @default.
- W2573350151 cites W2293597654 @default.
- W2573350151 cites W2402125293 @default.
- W2573350151 cites W2436219157 @default.
- W2573350151 cites W2912565010 @default.
- W2573350151 cites W2951004968 @default.
- W2573350151 cites W2951592057 @default.
- W2573350151 cites W2951692027 @default.
- W2573350151 cites W2952264928 @default.
- W2573350151 cites W2963619462 @default.
- W2573350151 cites W3118608800 @default.
- W2573350151 hasPublicationYear "2017" @default.
- W2573350151 type Work @default.
- W2573350151 sameAs 2573350151 @default.
- W2573350151 citedByCount "7" @default.
- W2573350151 countsByYear W25733501512017 @default.
- W2573350151 countsByYear W25733501512018 @default.
- W2573350151 countsByYear W25733501512020 @default.
- W2573350151 countsByYear W25733501512021 @default.
- W2573350151 crossrefType "posted-content" @default.
- W2573350151 hasAuthorship W2573350151A5007775697 @default.
- W2573350151 hasAuthorship W2573350151A5018301052 @default.
- W2573350151 hasAuthorship W2573350151A5030589527 @default.
- W2573350151 hasAuthorship W2573350151A5071683073 @default.
- W2573350151 hasAuthorship W2573350151A5086484914 @default.
- W2573350151 hasConcept C11413529 @default.
- W2573350151 hasConcept C116058348 @default.
- W2573350151 hasConcept C119857082 @default.
- W2573350151 hasConcept C122907437 @default.
- W2573350151 hasConcept C133667856 @default.
- W2573350151 hasConcept C138111711 @default.
- W2573350151 hasConcept C154945302 @default.
- W2573350151 hasConcept C167966045 @default.
- W2573350151 hasConcept C33923547 @default.
- W2573350151 hasConcept C38652104 @default.
- W2573350151 hasConcept C39890363 @default.
- W2573350151 hasConcept C41008148 @default.
- W2573350151 hasConcept C48372109 @default.
- W2573350151 hasConcept C63435697 @default.
- W2573350151 hasConcept C67388219 @default.
- W2573350151 hasConcept C80444323 @default.
- W2573350151 hasConcept C94375191 @default.
- W2573350151 hasConcept C99138194 @default.
- W2573350151 hasConceptScore W2573350151C11413529 @default.
- W2573350151 hasConceptScore W2573350151C116058348 @default.
- W2573350151 hasConceptScore W2573350151C119857082 @default.
- W2573350151 hasConceptScore W2573350151C122907437 @default.
- W2573350151 hasConceptScore W2573350151C133667856 @default.
- W2573350151 hasConceptScore W2573350151C138111711 @default.
- W2573350151 hasConceptScore W2573350151C154945302 @default.
- W2573350151 hasConceptScore W2573350151C167966045 @default.
- W2573350151 hasConceptScore W2573350151C33923547 @default.
- W2573350151 hasConceptScore W2573350151C38652104 @default.
- W2573350151 hasConceptScore W2573350151C39890363 @default.
- W2573350151 hasConceptScore W2573350151C41008148 @default.
- W2573350151 hasConceptScore W2573350151C48372109 @default.
- W2573350151 hasConceptScore W2573350151C63435697 @default.
- W2573350151 hasConceptScore W2573350151C67388219 @default.
- W2573350151 hasConceptScore W2573350151C80444323 @default.
- W2573350151 hasConceptScore W2573350151C94375191 @default.
- W2573350151 hasConceptScore W2573350151C99138194 @default.
- W2573350151 hasLocation W25733501511 @default.
- W2573350151 hasOpenAccess W2573350151 @default.
- W2573350151 hasPrimaryLocation W25733501511 @default.
- W2573350151 hasRelatedWork W1502916507 @default.
- W2573350151 hasRelatedWork W1522301498 @default.
- W2573350151 hasRelatedWork W1939575207 @default.
- W2573350151 hasRelatedWork W1956333070 @default.
- W2573350151 hasRelatedWork W1974647172 @default.
- W2573350151 hasRelatedWork W2007972815 @default.
- W2573350151 hasRelatedWork W2029205712 @default.
- W2573350151 hasRelatedWork W2108598243 @default.