Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210885000> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4210885000 endingPage "606" @default.
- W4210885000 startingPage "602" @default.
- W4210885000 abstract "Hashing has attracted increasing attention in image retrieval recently due to its storage and computational efficiency. Although several deep unsupervised hashing methods have been proposed lately, their effectiveness is far from satisfactory in practice owing to two drawbacks. On the one hand, they mostly construct binary similarity matrices which could neglect the confidence differences among multiple similarity signals. On the other hand, they ignore the desired properties of hash codes (i.e., independence and robustness). In this paper, we propose an effective unsupervised hashing method called <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>H</b> ashing via <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>S</b> tructural and <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>I</b> ntrinsic si <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>M</b> ilarity learning (HashSIM) to tackle these issues in an end-to-end manner. Specifically, HashSIM utilizes both highly and normally confident image pairs to jointly build a continuous similarity matrix, which guides hash code learning via structural similarity learning. Moreover, inspired by contrastive learning, we impose an intrinsic similarity learning objective, which can maximally satisfy the independence and robustness properties of hash bits. Extensive experiments on three popular benchmark datasets demonstrate that our HashSIM outperforms a broad range of state-of-the-art baselines." @default.
- W4210885000 created "2022-02-09" @default.
- W4210885000 creator A5030001981 @default.
- W4210885000 creator A5037724644 @default.
- W4210885000 creator A5073859117 @default.
- W4210885000 creator A5091013880 @default.
- W4210885000 date "2022-01-01" @default.
- W4210885000 modified "2023-10-18" @default.
- W4210885000 title "Improve Deep Unsupervised Hashing via Structural and Intrinsic Similarity Learning" @default.
- W4210885000 cites W1910300841 @default.
- W4210885000 cites W1936825185 @default.
- W4210885000 cites W1956333070 @default.
- W4210885000 cites W1974647172 @default.
- W4210885000 cites W2007972815 @default.
- W4210885000 cites W2029205712 @default.
- W4210885000 cites W2040918046 @default.
- W4210885000 cites W2155803963 @default.
- W4210885000 cites W2411707397 @default.
- W4210885000 cites W2461086877 @default.
- W4210885000 cites W2509619282 @default.
- W4210885000 cites W2766724094 @default.
- W4210885000 cites W2808282156 @default.
- W4210885000 cites W2891893825 @default.
- W4210885000 cites W2951952490 @default.
- W4210885000 cites W2963469388 @default.
- W4210885000 cites W2963916624 @default.
- W4210885000 cites W2964158883 @default.
- W4210885000 cites W2970518483 @default.
- W4210885000 cites W3014701888 @default.
- W4210885000 cites W3025665229 @default.
- W4210885000 cites W3033740891 @default.
- W4210885000 cites W3034205626 @default.
- W4210885000 cites W3034876737 @default.
- W4210885000 cites W3040948901 @default.
- W4210885000 cites W3093116134 @default.
- W4210885000 cites W3096463738 @default.
- W4210885000 cites W3108682246 @default.
- W4210885000 cites W3135261490 @default.
- W4210885000 cites W3171515703 @default.
- W4210885000 cites W3200993057 @default.
- W4210885000 doi "https://doi.org/10.1109/lsp.2022.3148674" @default.
- W4210885000 hasPublicationYear "2022" @default.
- W4210885000 type Work @default.
- W4210885000 citedByCount "4" @default.
- W4210885000 countsByYear W42108850002023 @default.
- W4210885000 crossrefType "journal-article" @default.
- W4210885000 hasAuthorship W4210885000A5030001981 @default.
- W4210885000 hasAuthorship W4210885000A5037724644 @default.
- W4210885000 hasAuthorship W4210885000A5073859117 @default.
- W4210885000 hasAuthorship W4210885000A5091013880 @default.
- W4210885000 hasConcept C103278499 @default.
- W4210885000 hasConcept C104317684 @default.
- W4210885000 hasConcept C115961682 @default.
- W4210885000 hasConcept C119857082 @default.
- W4210885000 hasConcept C154945302 @default.
- W4210885000 hasConcept C185592680 @default.
- W4210885000 hasConcept C38652104 @default.
- W4210885000 hasConcept C41008148 @default.
- W4210885000 hasConcept C55493867 @default.
- W4210885000 hasConcept C63479239 @default.
- W4210885000 hasConcept C80444323 @default.
- W4210885000 hasConcept C99138194 @default.
- W4210885000 hasConceptScore W4210885000C103278499 @default.
- W4210885000 hasConceptScore W4210885000C104317684 @default.
- W4210885000 hasConceptScore W4210885000C115961682 @default.
- W4210885000 hasConceptScore W4210885000C119857082 @default.
- W4210885000 hasConceptScore W4210885000C154945302 @default.
- W4210885000 hasConceptScore W4210885000C185592680 @default.
- W4210885000 hasConceptScore W4210885000C38652104 @default.
- W4210885000 hasConceptScore W4210885000C41008148 @default.
- W4210885000 hasConceptScore W4210885000C55493867 @default.
- W4210885000 hasConceptScore W4210885000C63479239 @default.
- W4210885000 hasConceptScore W4210885000C80444323 @default.
- W4210885000 hasConceptScore W4210885000C99138194 @default.
- W4210885000 hasFunder F4320321001 @default.
- W4210885000 hasLocation W42108850001 @default.
- W4210885000 hasOpenAccess W4210885000 @default.
- W4210885000 hasPrimaryLocation W42108850001 @default.
- W4210885000 hasRelatedWork W2961085424 @default.
- W4210885000 hasRelatedWork W3041052722 @default.
- W4210885000 hasRelatedWork W3046775127 @default.
- W4210885000 hasRelatedWork W3170094116 @default.
- W4210885000 hasRelatedWork W4205958290 @default.
- W4210885000 hasRelatedWork W4285260836 @default.
- W4210885000 hasRelatedWork W4286629047 @default.
- W4210885000 hasRelatedWork W4306321456 @default.
- W4210885000 hasRelatedWork W4306674287 @default.
- W4210885000 hasRelatedWork W4224009465 @default.
- W4210885000 hasVolume "29" @default.
- W4210885000 isParatext "false" @default.
- W4210885000 isRetracted "false" @default.
- W4210885000 workType "article" @default.