Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897656415> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2897656415 abstract "Deep hashing establishes efficient and effective image retrieval by end-to-end learning of deep representations and hash codes from similarity data. We present a compact coding solution, focusing on deep learning to quantization approach that has shown superior performance over hashing solutions for similarity retrieval. We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets. To enable more effective triplet training, we design a new triplet selection approach, Group Hard, that randomly selects hard triplets in each image group. To generate compact binary codes, we further apply a triplet quantization with weak orthogonality during triplet training. The quantization loss reduces the codebook redundancy and enhances the quantizability of deep representations through back-propagation. Extensive experiments demonstrate that DTQ can generate high-quality and compact binary codes, which yields state-of-the-art image retrieval performance on three benchmark datasets, NUS-WIDE, CIFAR-10, and MS-COCO." @default.
- W2897656415 created "2018-10-26" @default.
- W2897656415 creator A5000839872 @default.
- W2897656415 creator A5019241553 @default.
- W2897656415 creator A5028650738 @default.
- W2897656415 creator A5062713558 @default.
- W2897656415 creator A5075880303 @default.
- W2897656415 date "2018-10-15" @default.
- W2897656415 modified "2023-09-25" @default.
- W2897656415 title "Deep Triplet Quantization" @default.
- W2897656415 cites W1972036246 @default.
- W2897656415 cites W1996936615 @default.
- W2897656415 cites W2007972815 @default.
- W2897656415 cites W2074668987 @default.
- W2897656415 cites W2077815765 @default.
- W2897656415 cites W2084363474 @default.
- W2897656415 cites W2124509324 @default.
- W2897656415 cites W2162064258 @default.
- W2897656415 cites W2411707397 @default.
- W2897656415 cites W2473499128 @default.
- W2897656415 cites W2508837377 @default.
- W2897656415 cites W2562322388 @default.
- W2897656415 cites W2738649458 @default.
- W2897656415 cites W2964304299 @default.
- W2897656415 cites W3098232083 @default.
- W2897656415 doi "https://doi.org/10.1145/3240508.3240516" @default.
- W2897656415 hasPublicationYear "2018" @default.
- W2897656415 type Work @default.
- W2897656415 sameAs 2897656415 @default.
- W2897656415 citedByCount "63" @default.
- W2897656415 countsByYear W28976564152018 @default.
- W2897656415 countsByYear W28976564152019 @default.
- W2897656415 countsByYear W28976564152020 @default.
- W2897656415 countsByYear W28976564152021 @default.
- W2897656415 countsByYear W28976564152022 @default.
- W2897656415 countsByYear W28976564152023 @default.
- W2897656415 crossrefType "proceedings-article" @default.
- W2897656415 hasAuthorship W2897656415A5000839872 @default.
- W2897656415 hasAuthorship W2897656415A5019241553 @default.
- W2897656415 hasAuthorship W2897656415A5028650738 @default.
- W2897656415 hasAuthorship W2897656415A5062713558 @default.
- W2897656415 hasAuthorship W2897656415A5075880303 @default.
- W2897656415 hasBestOaLocation W28976564152 @default.
- W2897656415 hasConcept C108583219 @default.
- W2897656415 hasConcept C11413529 @default.
- W2897656415 hasConcept C115961682 @default.
- W2897656415 hasConcept C127759330 @default.
- W2897656415 hasConcept C153180895 @default.
- W2897656415 hasConcept C154945302 @default.
- W2897656415 hasConcept C1667742 @default.
- W2897656415 hasConcept C193319292 @default.
- W2897656415 hasConcept C28855332 @default.
- W2897656415 hasConcept C33923547 @default.
- W2897656415 hasConcept C38652104 @default.
- W2897656415 hasConcept C41008148 @default.
- W2897656415 hasConcept C48372109 @default.
- W2897656415 hasConcept C63435697 @default.
- W2897656415 hasConcept C80444323 @default.
- W2897656415 hasConcept C94375191 @default.
- W2897656415 hasConcept C99138194 @default.
- W2897656415 hasConceptScore W2897656415C108583219 @default.
- W2897656415 hasConceptScore W2897656415C11413529 @default.
- W2897656415 hasConceptScore W2897656415C115961682 @default.
- W2897656415 hasConceptScore W2897656415C127759330 @default.
- W2897656415 hasConceptScore W2897656415C153180895 @default.
- W2897656415 hasConceptScore W2897656415C154945302 @default.
- W2897656415 hasConceptScore W2897656415C1667742 @default.
- W2897656415 hasConceptScore W2897656415C193319292 @default.
- W2897656415 hasConceptScore W2897656415C28855332 @default.
- W2897656415 hasConceptScore W2897656415C33923547 @default.
- W2897656415 hasConceptScore W2897656415C38652104 @default.
- W2897656415 hasConceptScore W2897656415C41008148 @default.
- W2897656415 hasConceptScore W2897656415C48372109 @default.
- W2897656415 hasConceptScore W2897656415C63435697 @default.
- W2897656415 hasConceptScore W2897656415C80444323 @default.
- W2897656415 hasConceptScore W2897656415C94375191 @default.
- W2897656415 hasConceptScore W2897656415C99138194 @default.
- W2897656415 hasLocation W28976564151 @default.
- W2897656415 hasLocation W28976564152 @default.
- W2897656415 hasOpenAccess W2897656415 @default.
- W2897656415 hasPrimaryLocation W28976564151 @default.
- W2897656415 hasRelatedWork W1997379154 @default.
- W2897656415 hasRelatedWork W2767557801 @default.
- W2897656415 hasRelatedWork W2884006160 @default.
- W2897656415 hasRelatedWork W2890989050 @default.
- W2897656415 hasRelatedWork W2896914719 @default.
- W2897656415 hasRelatedWork W2897656415 @default.
- W2897656415 hasRelatedWork W2900531385 @default.
- W2897656415 hasRelatedWork W3023116810 @default.
- W2897656415 hasRelatedWork W4212944455 @default.
- W2897656415 hasRelatedWork W4225654135 @default.
- W2897656415 isParatext "false" @default.
- W2897656415 isRetracted "false" @default.
- W2897656415 magId "2897656415" @default.
- W2897656415 workType "article" @default.