Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383532766> ?p ?o ?g. }
- W4383532766 endingPage "117017" @default.
- W4383532766 startingPage "117017" @default.
- W4383532766 abstract "Deep cross-modal hashing has made great progress in recent years due to the development of deep learning and efficient hashing algorithms. However, most of the existing methods only focus on the feature distribution between modalities, and ignore the fine grain information in each modality. To solve this problem, we propose a multi-level adversarial attention cross-modal hashing (MAAH). First, we design a modality-attention module to find the fine-grained information of each modality. Specifically, we use the channel attention mechanism to divide modality information into relevant and irrelevant representation, in which the irrelevant representation is the fine-grained information of the modality. Then, we design a modality-adversary module to supplement the fine-grained information of each modality. In this module, intra-modal adversarial learning can supplement the relevant representation of modalities, and inter-modal adversarial learning can make the distribution of the relevant representation of each modality more uniform. Experimental results on three widely used datasets demonstrate the superiority of the proposed method." @default.
- W4383532766 created "2023-07-08" @default.
- W4383532766 creator A5010451532 @default.
- W4383532766 creator A5036777291 @default.
- W4383532766 creator A5038612499 @default.
- W4383532766 creator A5057820981 @default.
- W4383532766 creator A5063481044 @default.
- W4383532766 date "2023-09-01" @default.
- W4383532766 modified "2023-10-09" @default.
- W4383532766 title "Multi-level adversarial attention cross-modal hashing" @default.
- W4383532766 cites W2015175493 @default.
- W4383532766 cites W2549070563 @default.
- W4383532766 cites W2564325886 @default.
- W4383532766 cites W2889024947 @default.
- W4383532766 cites W2907166662 @default.
- W4383532766 cites W2974497444 @default.
- W4383532766 cites W2999606372 @default.
- W4383532766 cites W3006962461 @default.
- W4383532766 cites W3030772386 @default.
- W4383532766 cites W3097639209 @default.
- W4383532766 cites W3169788532 @default.
- W4383532766 doi "https://doi.org/10.1016/j.image.2023.117017" @default.
- W4383532766 hasPublicationYear "2023" @default.
- W4383532766 type Work @default.
- W4383532766 citedByCount "0" @default.
- W4383532766 crossrefType "journal-article" @default.
- W4383532766 hasAuthorship W4383532766A5010451532 @default.
- W4383532766 hasAuthorship W4383532766A5036777291 @default.
- W4383532766 hasAuthorship W4383532766A5038612499 @default.
- W4383532766 hasAuthorship W4383532766A5057820981 @default.
- W4383532766 hasAuthorship W4383532766A5063481044 @default.
- W4383532766 hasConcept C108583219 @default.
- W4383532766 hasConcept C119857082 @default.
- W4383532766 hasConcept C120665830 @default.
- W4383532766 hasConcept C121332964 @default.
- W4383532766 hasConcept C138885662 @default.
- W4383532766 hasConcept C144024400 @default.
- W4383532766 hasConcept C154945302 @default.
- W4383532766 hasConcept C17744445 @default.
- W4383532766 hasConcept C185592680 @default.
- W4383532766 hasConcept C188027245 @default.
- W4383532766 hasConcept C192209626 @default.
- W4383532766 hasConcept C199539241 @default.
- W4383532766 hasConcept C2776359362 @default.
- W4383532766 hasConcept C2776401178 @default.
- W4383532766 hasConcept C2779903281 @default.
- W4383532766 hasConcept C2780226545 @default.
- W4383532766 hasConcept C36289849 @default.
- W4383532766 hasConcept C37736160 @default.
- W4383532766 hasConcept C38652104 @default.
- W4383532766 hasConcept C41008148 @default.
- W4383532766 hasConcept C41895202 @default.
- W4383532766 hasConcept C59404180 @default.
- W4383532766 hasConcept C71139939 @default.
- W4383532766 hasConcept C80444323 @default.
- W4383532766 hasConcept C94625758 @default.
- W4383532766 hasConcept C99138194 @default.
- W4383532766 hasConceptScore W4383532766C108583219 @default.
- W4383532766 hasConceptScore W4383532766C119857082 @default.
- W4383532766 hasConceptScore W4383532766C120665830 @default.
- W4383532766 hasConceptScore W4383532766C121332964 @default.
- W4383532766 hasConceptScore W4383532766C138885662 @default.
- W4383532766 hasConceptScore W4383532766C144024400 @default.
- W4383532766 hasConceptScore W4383532766C154945302 @default.
- W4383532766 hasConceptScore W4383532766C17744445 @default.
- W4383532766 hasConceptScore W4383532766C185592680 @default.
- W4383532766 hasConceptScore W4383532766C188027245 @default.
- W4383532766 hasConceptScore W4383532766C192209626 @default.
- W4383532766 hasConceptScore W4383532766C199539241 @default.
- W4383532766 hasConceptScore W4383532766C2776359362 @default.
- W4383532766 hasConceptScore W4383532766C2776401178 @default.
- W4383532766 hasConceptScore W4383532766C2779903281 @default.
- W4383532766 hasConceptScore W4383532766C2780226545 @default.
- W4383532766 hasConceptScore W4383532766C36289849 @default.
- W4383532766 hasConceptScore W4383532766C37736160 @default.
- W4383532766 hasConceptScore W4383532766C38652104 @default.
- W4383532766 hasConceptScore W4383532766C41008148 @default.
- W4383532766 hasConceptScore W4383532766C41895202 @default.
- W4383532766 hasConceptScore W4383532766C59404180 @default.
- W4383532766 hasConceptScore W4383532766C71139939 @default.
- W4383532766 hasConceptScore W4383532766C80444323 @default.
- W4383532766 hasConceptScore W4383532766C94625758 @default.
- W4383532766 hasConceptScore W4383532766C99138194 @default.
- W4383532766 hasLocation W43835327661 @default.
- W4383532766 hasOpenAccess W4383532766 @default.
- W4383532766 hasPrimaryLocation W43835327661 @default.
- W4383532766 hasRelatedWork W2004831463 @default.
- W4383532766 hasRelatedWork W2110287964 @default.
- W4383532766 hasRelatedWork W2383394264 @default.
- W4383532766 hasRelatedWork W3125968744 @default.
- W4383532766 hasRelatedWork W4224266612 @default.
- W4383532766 hasRelatedWork W4293261942 @default.
- W4383532766 hasRelatedWork W4307407935 @default.
- W4383532766 hasRelatedWork W4320153225 @default.
- W4383532766 hasRelatedWork W73545470 @default.
- W4383532766 hasRelatedWork W649759291 @default.
- W4383532766 hasVolume "117" @default.
- W4383532766 isParatext "false" @default.