Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312683822> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4312683822 abstract "With the rapid progress of medical image technology, medical image retrieval has attracted wide attention in medical data processing fields. Deep hashing methods have been proven effective for massive medical image retrieval. However, existing medical image retrieval methods ignore lesion context and category-level semantics, so it is difficult to correctly correspond to the context information and category of the lesion, resulting in poor performance. This paper addresses this dilemma with a novel Deep Semantic Ranking Hashing Based on Self-Attention (DSHA) approach. We first divide the medical triplet into smaller patches and send them to the multi-head self-attention module, which can more effectively encode the context information of the lesion and the interaction among patches. Meanwhile, the weight-sharing triplet networks are used to learn hash codes, which are forced to be semantically aligned. The proposed semantic enhancement loss effectively enhances the category-level semantics of hash codes. In addition, we added a semantic ranking penalty loss to optimize the retrieval accuracy. Extensive experiments on diverse medical image datasets prove that our DSHA method achieves remarkable results compared with the state-of-the-art medical image retrieval methods." @default.
- W4312683822 created "2023-01-05" @default.
- W4312683822 creator A5002872475 @default.
- W4312683822 creator A5003775716 @default.
- W4312683822 creator A5029329863 @default.
- W4312683822 date "2022-08-21" @default.
- W4312683822 modified "2023-09-28" @default.
- W4312683822 title "Deep Semantic Ranking Hashing Based on Self-Attention for Medical Image Retrieval" @default.
- W4312683822 cites W2009573349 @default.
- W4312683822 cites W2034196113 @default.
- W4312683822 cites W2084363474 @default.
- W4312683822 cites W2464915613 @default.
- W4312683822 cites W2587224204 @default.
- W4312683822 cites W2592929672 @default.
- W4312683822 cites W2753282939 @default.
- W4312683822 cites W2760880057 @default.
- W4312683822 cites W2884585870 @default.
- W4312683822 cites W2920852583 @default.
- W4312683822 cites W2952898185 @default.
- W4312683822 cites W2963091558 @default.
- W4312683822 cites W2966218308 @default.
- W4312683822 cites W3093149564 @default.
- W4312683822 cites W3128345400 @default.
- W4312683822 cites W3129137136 @default.
- W4312683822 cites W3135057764 @default.
- W4312683822 doi "https://doi.org/10.1109/icpr56361.2022.9956369" @default.
- W4312683822 hasPublicationYear "2022" @default.
- W4312683822 type Work @default.
- W4312683822 citedByCount "0" @default.
- W4312683822 crossrefType "proceedings-article" @default.
- W4312683822 hasAuthorship W4312683822A5002872475 @default.
- W4312683822 hasAuthorship W4312683822A5003775716 @default.
- W4312683822 hasAuthorship W4312683822A5029329863 @default.
- W4312683822 hasConcept C115961682 @default.
- W4312683822 hasConcept C151730666 @default.
- W4312683822 hasConcept C154945302 @default.
- W4312683822 hasConcept C1667742 @default.
- W4312683822 hasConcept C184337299 @default.
- W4312683822 hasConcept C189430467 @default.
- W4312683822 hasConcept C199360897 @default.
- W4312683822 hasConcept C23123220 @default.
- W4312683822 hasConcept C2779343474 @default.
- W4312683822 hasConcept C38652104 @default.
- W4312683822 hasConcept C41008148 @default.
- W4312683822 hasConcept C86803240 @default.
- W4312683822 hasConcept C99138194 @default.
- W4312683822 hasConceptScore W4312683822C115961682 @default.
- W4312683822 hasConceptScore W4312683822C151730666 @default.
- W4312683822 hasConceptScore W4312683822C154945302 @default.
- W4312683822 hasConceptScore W4312683822C1667742 @default.
- W4312683822 hasConceptScore W4312683822C184337299 @default.
- W4312683822 hasConceptScore W4312683822C189430467 @default.
- W4312683822 hasConceptScore W4312683822C199360897 @default.
- W4312683822 hasConceptScore W4312683822C23123220 @default.
- W4312683822 hasConceptScore W4312683822C2779343474 @default.
- W4312683822 hasConceptScore W4312683822C38652104 @default.
- W4312683822 hasConceptScore W4312683822C41008148 @default.
- W4312683822 hasConceptScore W4312683822C86803240 @default.
- W4312683822 hasConceptScore W4312683822C99138194 @default.
- W4312683822 hasFunder F4320324638 @default.
- W4312683822 hasFunder F4320335787 @default.
- W4312683822 hasLocation W43126838221 @default.
- W4312683822 hasOpenAccess W4312683822 @default.
- W4312683822 hasPrimaryLocation W43126838221 @default.
- W4312683822 hasRelatedWork W2000806578 @default.
- W4312683822 hasRelatedWork W2027614354 @default.
- W4312683822 hasRelatedWork W2088097596 @default.
- W4312683822 hasRelatedWork W2297217129 @default.
- W4312683822 hasRelatedWork W2355264470 @default.
- W4312683822 hasRelatedWork W2386008290 @default.
- W4312683822 hasRelatedWork W2808503949 @default.
- W4312683822 hasRelatedWork W3097853387 @default.
- W4312683822 hasRelatedWork W3214915308 @default.
- W4312683822 hasRelatedWork W4232395208 @default.
- W4312683822 isParatext "false" @default.
- W4312683822 isRetracted "false" @default.
- W4312683822 workType "article" @default.