Matches in SemOpenAlex for { <https://semopenalex.org/work/W2966747399> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2966747399 abstract "In recent years, increasing deep hashing methods have been applied in large-scale multi-label image retrieval. However, in the existing deep network models, the extracted low-level features cannot effectively integrate the multi-level semantic information and the similarity ranking information of pairwise multi-label images into one hash coding learning scheme. Therefore, we cannot obtain an efficient and accurate index method. Motivated by this, in this paper, we proposed a novel approach adopting the cosine distance of pairwise multi-label images semantic vector to quantify existing multi-level similarity in a multi-label image. Meanwhile, we utilized the residual network to learn the final representation of multi-label images features. Finally, we constructed a deep hashing framework to extract features and generate binary codes simultaneously. On the one hand, the improved model uses a deeper network and more complex network structures to enhance the ability of low-level features extraction. On the other hand, the improved model was trained by a fine-tuning strategy, which can accelerate the convergence speed. Extensive experiments on two popular multi-label datasets demonstrate that the improved model outperforms the reference models regarding accuracy. The mean average precision is improved by 1.0432 and 1.1114 times on two datasets, respectively." @default.
- W2966747399 created "2019-08-13" @default.
- W2966747399 creator A5008213911 @default.
- W2966747399 creator A5014075636 @default.
- W2966747399 creator A5039192135 @default.
- W2966747399 creator A5044652658 @default.
- W2966747399 creator A5054610344 @default.
- W2966747399 creator A5080734422 @default.
- W2966747399 creator A5089327541 @default.
- W2966747399 date "2019-06-01" @default.
- W2966747399 modified "2023-10-02" @default.
- W2966747399 title "Large-scale Multi-label Image Retrieval Using Residual Network with Hash Layer" @default.
- W2966747399 doi "https://doi.org/10.1109/icaci.2019.8778549" @default.
- W2966747399 hasPublicationYear "2019" @default.
- W2966747399 type Work @default.
- W2966747399 sameAs 2966747399 @default.
- W2966747399 citedByCount "1" @default.
- W2966747399 countsByYear W29667473992020 @default.
- W2966747399 crossrefType "proceedings-article" @default.
- W2966747399 hasAuthorship W2966747399A5008213911 @default.
- W2966747399 hasAuthorship W2966747399A5014075636 @default.
- W2966747399 hasAuthorship W2966747399A5039192135 @default.
- W2966747399 hasAuthorship W2966747399A5044652658 @default.
- W2966747399 hasAuthorship W2966747399A5054610344 @default.
- W2966747399 hasAuthorship W2966747399A5080734422 @default.
- W2966747399 hasAuthorship W2966747399A5089327541 @default.
- W2966747399 hasConcept C108583219 @default.
- W2966747399 hasConcept C11413529 @default.
- W2966747399 hasConcept C115961682 @default.
- W2966747399 hasConcept C124101348 @default.
- W2966747399 hasConcept C153180895 @default.
- W2966747399 hasConcept C154945302 @default.
- W2966747399 hasConcept C155512373 @default.
- W2966747399 hasConcept C1667742 @default.
- W2966747399 hasConcept C184898388 @default.
- W2966747399 hasConcept C2780762811 @default.
- W2966747399 hasConcept C38652104 @default.
- W2966747399 hasConcept C41008148 @default.
- W2966747399 hasConcept C67388219 @default.
- W2966747399 hasConcept C74270461 @default.
- W2966747399 hasConcept C99138194 @default.
- W2966747399 hasConceptScore W2966747399C108583219 @default.
- W2966747399 hasConceptScore W2966747399C11413529 @default.
- W2966747399 hasConceptScore W2966747399C115961682 @default.
- W2966747399 hasConceptScore W2966747399C124101348 @default.
- W2966747399 hasConceptScore W2966747399C153180895 @default.
- W2966747399 hasConceptScore W2966747399C154945302 @default.
- W2966747399 hasConceptScore W2966747399C155512373 @default.
- W2966747399 hasConceptScore W2966747399C1667742 @default.
- W2966747399 hasConceptScore W2966747399C184898388 @default.
- W2966747399 hasConceptScore W2966747399C2780762811 @default.
- W2966747399 hasConceptScore W2966747399C38652104 @default.
- W2966747399 hasConceptScore W2966747399C41008148 @default.
- W2966747399 hasConceptScore W2966747399C67388219 @default.
- W2966747399 hasConceptScore W2966747399C74270461 @default.
- W2966747399 hasConceptScore W2966747399C99138194 @default.
- W2966747399 hasLocation W29667473991 @default.
- W2966747399 hasOpenAccess W2966747399 @default.
- W2966747399 hasPrimaryLocation W29667473991 @default.
- W2966747399 hasRelatedWork W2015060894 @default.
- W2966747399 hasRelatedWork W2742121874 @default.
- W2966747399 hasRelatedWork W2767252287 @default.
- W2966747399 hasRelatedWork W2803163484 @default.
- W2966747399 hasRelatedWork W2901351317 @default.
- W2966747399 hasRelatedWork W2935160886 @default.
- W2966747399 hasRelatedWork W2973288832 @default.
- W2966747399 hasRelatedWork W3004566834 @default.
- W2966747399 hasRelatedWork W3005728763 @default.
- W2966747399 hasRelatedWork W3006871679 @default.
- W2966747399 hasRelatedWork W3014419292 @default.
- W2966747399 hasRelatedWork W3015471782 @default.
- W2966747399 hasRelatedWork W3021521120 @default.
- W2966747399 hasRelatedWork W3108682246 @default.
- W2966747399 hasRelatedWork W3115235400 @default.
- W2966747399 hasRelatedWork W3141336300 @default.
- W2966747399 hasRelatedWork W3176317965 @default.
- W2966747399 hasRelatedWork W3206688619 @default.
- W2966747399 hasRelatedWork W3001037527 @default.
- W2966747399 hasRelatedWork W3019668446 @default.
- W2966747399 isParatext "false" @default.
- W2966747399 isRetracted "false" @default.
- W2966747399 magId "2966747399" @default.
- W2966747399 workType "article" @default.