Matches in SemOpenAlex for { <https://semopenalex.org/work/W3021521120> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3021521120 endingPage "59" @default.
- W3021521120 startingPage "46" @default.
- W3021521120 abstract "Abstract For multi-label image retrieval based on deep hashing, the ultimate challenge is to map from the original image to binary space while preserving high-level semantic similarity. Recently, many supervised deep hashing approaches for multi-label image retrieval have been proposed to generate high-quality binary codes. However, most such methods are only introduced to learn simple similarity based on these image characteristics, therein ignoring complex multilevel semantic similarity with fine-grained features. In this paper, we propose a framework named deep hashing with fine-grained feature learning (DH-FFL) to preserve complex multilevel semantic similarity between multi-label image pairs. In this proposed model, compact bilinear pooling convolutional neural networks (CNNs) with normalization are adopted to extract fine-grained feature descriptors. In addition, a novel multilevel contrastive loss is designed to preserve multilevel semantic similarity by introducing a zero-loss parameter. Moreover, a multi-label classification loss is used to maintain the unique semantic structure of each image and maximize the distinguishing ability of binary codes. Comprehensive experiments on three benchmark datasets show that the proposed DH-FFL achieves promising performance compared with other state-of-the-art multi-label image retrieval applications." @default.
- W3021521120 created "2020-05-13" @default.
- W3021521120 creator A5046223306 @default.
- W3021521120 creator A5079932099 @default.
- W3021521120 creator A5090798126 @default.
- W3021521120 date "2020-10-01" @default.
- W3021521120 modified "2023-10-17" @default.
- W3021521120 title "Deep multilevel similarity hashing with fine-grained features for multi-label image retrieval" @default.
- W3021521120 cites W1560344264 @default.
- W3021521120 cites W1910300841 @default.
- W3021521120 cites W1974647172 @default.
- W3021521120 cites W1990537115 @default.
- W3021521120 cites W1992371516 @default.
- W3021521120 cites W1997107867 @default.
- W3021521120 cites W2031489346 @default.
- W3021521120 cites W2082627290 @default.
- W3021521120 cites W2197560310 @default.
- W3021521120 cites W2345812103 @default.
- W3021521120 cites W2411707397 @default.
- W3021521120 cites W2464915613 @default.
- W3021521120 cites W2483935403 @default.
- W3021521120 cites W2586937979 @default.
- W3021521120 cites W2604669887 @default.
- W3021521120 cites W2751850814 @default.
- W3021521120 cites W2769908547 @default.
- W3021521120 cites W2791083848 @default.
- W3021521120 cites W2803163484 @default.
- W3021521120 cites W2895643041 @default.
- W3021521120 cites W2895933466 @default.
- W3021521120 cites W2897641604 @default.
- W3021521120 cites W2905957315 @default.
- W3021521120 cites W2922521335 @default.
- W3021521120 cites W2963213486 @default.
- W3021521120 cites W3103722964 @default.
- W3021521120 cites W3125882365 @default.
- W3021521120 cites W4251560691 @default.
- W3021521120 doi "https://doi.org/10.1016/j.neucom.2020.04.125" @default.
- W3021521120 hasPublicationYear "2020" @default.
- W3021521120 type Work @default.
- W3021521120 sameAs 3021521120 @default.
- W3021521120 citedByCount "4" @default.
- W3021521120 countsByYear W30215211202022 @default.
- W3021521120 countsByYear W30215211202023 @default.
- W3021521120 crossrefType "journal-article" @default.
- W3021521120 hasAuthorship W3021521120A5046223306 @default.
- W3021521120 hasAuthorship W3021521120A5079932099 @default.
- W3021521120 hasAuthorship W3021521120A5090798126 @default.
- W3021521120 hasConcept C103278499 @default.
- W3021521120 hasConcept C115961682 @default.
- W3021521120 hasConcept C116738811 @default.
- W3021521120 hasConcept C153180895 @default.
- W3021521120 hasConcept C154945302 @default.
- W3021521120 hasConcept C1667742 @default.
- W3021521120 hasConcept C38652104 @default.
- W3021521120 hasConcept C41008148 @default.
- W3021521120 hasConcept C67388219 @default.
- W3021521120 hasConcept C74270461 @default.
- W3021521120 hasConcept C99138194 @default.
- W3021521120 hasConceptScore W3021521120C103278499 @default.
- W3021521120 hasConceptScore W3021521120C115961682 @default.
- W3021521120 hasConceptScore W3021521120C116738811 @default.
- W3021521120 hasConceptScore W3021521120C153180895 @default.
- W3021521120 hasConceptScore W3021521120C154945302 @default.
- W3021521120 hasConceptScore W3021521120C1667742 @default.
- W3021521120 hasConceptScore W3021521120C38652104 @default.
- W3021521120 hasConceptScore W3021521120C41008148 @default.
- W3021521120 hasConceptScore W3021521120C67388219 @default.
- W3021521120 hasConceptScore W3021521120C74270461 @default.
- W3021521120 hasConceptScore W3021521120C99138194 @default.
- W3021521120 hasFunder F4320321001 @default.
- W3021521120 hasFunder F4320324174 @default.
- W3021521120 hasLocation W30215211201 @default.
- W3021521120 hasOpenAccess W3021521120 @default.
- W3021521120 hasPrimaryLocation W30215211201 @default.
- W3021521120 hasRelatedWork W2118410043 @default.
- W3021521120 hasRelatedWork W2156855109 @default.
- W3021521120 hasRelatedWork W2754457794 @default.
- W3021521120 hasRelatedWork W2953235529 @default.
- W3021521120 hasRelatedWork W2982071482 @default.
- W3021521120 hasRelatedWork W3011415302 @default.
- W3021521120 hasRelatedWork W3035166804 @default.
- W3021521120 hasRelatedWork W3121915774 @default.
- W3021521120 hasRelatedWork W3175354525 @default.
- W3021521120 hasRelatedWork W4300918469 @default.
- W3021521120 hasVolume "409" @default.
- W3021521120 isParatext "false" @default.
- W3021521120 isRetracted "false" @default.
- W3021521120 magId "3021521120" @default.
- W3021521120 workType "article" @default.