Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296177787> ?p ?o ?g. }
- W4296177787 endingPage "109888" @default.
- W4296177787 startingPage "109888" @default.
- W4296177787 abstract "Batch-based cross-modal hashing retrieval methods have made great progress. However, they could not be applied in scenarios where new data continuously arrives in a stream. To this end, a few online cross-modal hashing retrieval methods have been proposed. However, they are based on shallow models, which may result in a suboptimal retrieval performance. Therefore, we propose Deep Online Cross-modal Hashing by a Co-training Mechanism (DOCHCM), which introduces deep learning to online cross-modal hashing by cooperatively training two subnetworks with two stages. DOCHCM addresses two problematics aspects. First, in each round, the image sub-network incrementally learns the hash codes of the current chunk of images by preserving the semantic similarity between their output features and the hash codes of the whole texts. The text sub-network incrementally learns the hash codes of the current chunk of texts by preserving the semantic similarity between their output features and the hash codes of the whole images. Second, knowledge distillation is leveraged to the image and text sub-networks to avoid catastrophic forgetting, which enables the two sub-networks not only to learn new knowledge but also to prevent the forgetting of the old knowledge. Extensive experiments on three benchmark datasets demonstrate that DOCHCM outperforms the state-of-the-art cross-modal hashing retrieval methods." @default.
- W4296177787 created "2022-09-18" @default.
- W4296177787 creator A5016786299 @default.
- W4296177787 creator A5063402485 @default.
- W4296177787 creator A5067064208 @default.
- W4296177787 creator A5067882740 @default.
- W4296177787 creator A5078693770 @default.
- W4296177787 date "2022-12-01" @default.
- W4296177787 modified "2023-10-14" @default.
- W4296177787 title "Deep online cross-modal hashing by a co-training mechanism" @default.
- W4296177787 cites W1910300841 @default.
- W4296177787 cites W1976258951 @default.
- W4296177787 cites W2086958058 @default.
- W4296177787 cites W2266728343 @default.
- W4296177787 cites W2281478935 @default.
- W4296177787 cites W2430055109 @default.
- W4296177787 cites W2515429244 @default.
- W4296177787 cites W2526152041 @default.
- W4296177787 cites W2535352129 @default.
- W4296177787 cites W2591669147 @default.
- W4296177787 cites W2593544735 @default.
- W4296177787 cites W2602646780 @default.
- W4296177787 cites W2740036143 @default.
- W4296177787 cites W2748725735 @default.
- W4296177787 cites W2802864907 @default.
- W4296177787 cites W2805134925 @default.
- W4296177787 cites W2894879246 @default.
- W4296177787 cites W2895876934 @default.
- W4296177787 cites W2897391546 @default.
- W4296177787 cites W2897841402 @default.
- W4296177787 cites W2903903916 @default.
- W4296177787 cites W2905097026 @default.
- W4296177787 cites W2906146234 @default.
- W4296177787 cites W2914320072 @default.
- W4296177787 cites W2955273087 @default.
- W4296177787 cites W2962786441 @default.
- W4296177787 cites W2963187862 @default.
- W4296177787 cites W2963288100 @default.
- W4296177787 cites W2982065678 @default.
- W4296177787 cites W2997578118 @default.
- W4296177787 cites W2999606372 @default.
- W4296177787 cites W3003735286 @default.
- W4296177787 cites W3006962461 @default.
- W4296177787 cites W3013615455 @default.
- W4296177787 cites W3022147900 @default.
- W4296177787 cites W3034876737 @default.
- W4296177787 cites W3034890701 @default.
- W4296177787 cites W3037158620 @default.
- W4296177787 cites W3092760908 @default.
- W4296177787 cites W3098232083 @default.
- W4296177787 cites W3128372581 @default.
- W4296177787 cites W3133145180 @default.
- W4296177787 cites W3168742240 @default.
- W4296177787 cites W3171255006 @default.
- W4296177787 cites W3175740157 @default.
- W4296177787 cites W3196246284 @default.
- W4296177787 cites W4200468977 @default.
- W4296177787 doi "https://doi.org/10.1016/j.knosys.2022.109888" @default.
- W4296177787 hasPublicationYear "2022" @default.
- W4296177787 type Work @default.
- W4296177787 citedByCount "1" @default.
- W4296177787 countsByYear W42961777872023 @default.
- W4296177787 crossrefType "journal-article" @default.
- W4296177787 hasAuthorship W4296177787A5016786299 @default.
- W4296177787 hasAuthorship W4296177787A5063402485 @default.
- W4296177787 hasAuthorship W4296177787A5067064208 @default.
- W4296177787 hasAuthorship W4296177787A5067882740 @default.
- W4296177787 hasAuthorship W4296177787A5078693770 @default.
- W4296177787 hasConcept C103278499 @default.
- W4296177787 hasConcept C108583219 @default.
- W4296177787 hasConcept C115961682 @default.
- W4296177787 hasConcept C119857082 @default.
- W4296177787 hasConcept C122907437 @default.
- W4296177787 hasConcept C124101348 @default.
- W4296177787 hasConcept C13280743 @default.
- W4296177787 hasConcept C133667856 @default.
- W4296177787 hasConcept C138111711 @default.
- W4296177787 hasConcept C138885662 @default.
- W4296177787 hasConcept C154945302 @default.
- W4296177787 hasConcept C185592680 @default.
- W4296177787 hasConcept C185798385 @default.
- W4296177787 hasConcept C188027245 @default.
- W4296177787 hasConcept C205649164 @default.
- W4296177787 hasConcept C23123220 @default.
- W4296177787 hasConcept C38652104 @default.
- W4296177787 hasConcept C41008148 @default.
- W4296177787 hasConcept C41895202 @default.
- W4296177787 hasConcept C67388219 @default.
- W4296177787 hasConcept C71139939 @default.
- W4296177787 hasConcept C7149132 @default.
- W4296177787 hasConcept C99138194 @default.
- W4296177787 hasConceptScore W4296177787C103278499 @default.
- W4296177787 hasConceptScore W4296177787C108583219 @default.
- W4296177787 hasConceptScore W4296177787C115961682 @default.
- W4296177787 hasConceptScore W4296177787C119857082 @default.
- W4296177787 hasConceptScore W4296177787C122907437 @default.
- W4296177787 hasConceptScore W4296177787C124101348 @default.
- W4296177787 hasConceptScore W4296177787C13280743 @default.