FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284977495> ?p ?o ?g. }

• W4284977495 endingPage "1502" @default.
• W4284977495 startingPage "1480" @default.
• W4284977495 abstract "The batch-based hash learning paradigm for uni-modal or cross-modal retrieval has made great progress in recent decades. However, methods that are based on this paradigm cannot adapt to the scenario of incoming new data streams continuously; in addition, they are inefficient in terms of training time and memory cost in big data searches because they have to accumulate all the database data and new incoming data before training. Although a few online hash retrieval methods have been proposed to address these issues in recent years, they are based on shallow models, and none of them can perform uni-modal and cross-modal retrieval in one framework. To this end, we propose a novel method, namely, Online Deep Hashing for both Uni-modal and Cross-modal retrieval (ODHUC). For online deep hashing, ODHUC first trains image and text neural networks with image and text fundamental databases, and their hash codes are learned. When new data arrive, ODHUC samples images and texts from the newly arriving data and fundamental databases to update the image and text networks and learn the hash codes of the new data, the aim of which is to keep the similarity of the hash codes of the incremental and old data consistent with the supervised semantic similarity. ODHUC is also trained with sampled old data by knowledge distillation to learn new knowledge and avoid catastrophic forgetting of old knowledge. In this way, ODHUC achieves online deep hash learning continually without performance decline. For two categories of retrieval tasks, ODHUC learns image and text deep hash functions in two stages to align image and text features; it generates image hash codes first and then utilizes them to supervise the text hash code learning. Thus, ODHUC can perform both uni-modal and cross-modal retrieval tasks in one framework. Extensive experiments on three real-world datasets demonstrate that ODHUC outperforms several state-of-the-art methods." @default.
• W4284977495 created "2022-07-10" @default.
• W4284977495 creator A5016786299 @default.
• W4284977495 creator A5063402485 @default.
• W4284977495 creator A5067882740 @default.
• W4284977495 creator A5087548970 @default.
• W4284977495 date "2022-08-01" @default.
• W4284977495 modified "2023-10-15" @default.
• W4284977495 title "Online deep hashing for both uni-modal and cross-modal retrieval" @default.
• W4284977495 cites W1893754589 @default.
• W4284977495 cites W2192994569 @default.
• W4284977495 cites W2430055109 @default.
• W4284977495 cites W2535352129 @default.
• W4284977495 cites W2740036143 @default.
• W4284977495 cites W2788843501 @default.
• W4284977495 cites W2795832645 @default.
• W4284977495 cites W2805134925 @default.
• W4284977495 cites W2809771837 @default.
• W4284977495 cites W2832876791 @default.
• W4284977495 cites W2903903916 @default.
• W4284977495 cites W2905097026 @default.
• W4284977495 cites W2906146234 @default.
• W4284977495 cites W2972421866 @default.
• W4284977495 cites W2997578118 @default.
• W4284977495 cites W2999606372 @default.
• W4284977495 cites W3000030185 @default.
• W4284977495 cites W3006962461 @default.
• W4284977495 cites W3013615455 @default.
• W4284977495 cites W3022147900 @default.
• W4284977495 cites W3025665229 @default.
• W4284977495 cites W3032908123 @default.
• W4284977495 cites W3036745850 @default.
• W4284977495 cites W3082744274 @default.
• W4284977495 cites W3106900108 @default.
• W4284977495 cites W3108818416 @default.
• W4284977495 cites W3162085601 @default.
• W4284977495 cites W3171255006 @default.
• W4284977495 cites W3196246284 @default.
• W4284977495 cites W3199266039 @default.
• W4284977495 doi "https://doi.org/10.1016/j.ins.2022.07.039" @default.
• W4284977495 hasPublicationYear "2022" @default.
• W4284977495 type Work @default.
• W4284977495 citedByCount "4" @default.
• W4284977495 countsByYear W42849774952023 @default.
• W4284977495 crossrefType "journal-article" @default.
• W4284977495 hasAuthorship W4284977495A5016786299 @default.
• W4284977495 hasAuthorship W4284977495A5063402485 @default.
• W4284977495 hasAuthorship W4284977495A5067882740 @default.
• W4284977495 hasAuthorship W4284977495A5087548970 @default.
• W4284977495 hasConcept C108583219 @default.
• W4284977495 hasConcept C115961682 @default.
• W4284977495 hasConcept C124101348 @default.
• W4284977495 hasConcept C133667856 @default.
• W4284977495 hasConcept C138111711 @default.
• W4284977495 hasConcept C154945302 @default.
• W4284977495 hasConcept C1667742 @default.
• W4284977495 hasConcept C185592680 @default.
• W4284977495 hasConcept C188027245 @default.
• W4284977495 hasConcept C23123220 @default.
• W4284977495 hasConcept C38652104 @default.
• W4284977495 hasConcept C41008148 @default.
• W4284977495 hasConcept C67388219 @default.
• W4284977495 hasConcept C71139939 @default.
• W4284977495 hasConcept C99138194 @default.
• W4284977495 hasConceptScore W4284977495C108583219 @default.
• W4284977495 hasConceptScore W4284977495C115961682 @default.
• W4284977495 hasConceptScore W4284977495C124101348 @default.
• W4284977495 hasConceptScore W4284977495C133667856 @default.
• W4284977495 hasConceptScore W4284977495C138111711 @default.
• W4284977495 hasConceptScore W4284977495C154945302 @default.
• W4284977495 hasConceptScore W4284977495C1667742 @default.
• W4284977495 hasConceptScore W4284977495C185592680 @default.
• W4284977495 hasConceptScore W4284977495C188027245 @default.
• W4284977495 hasConceptScore W4284977495C23123220 @default.
• W4284977495 hasConceptScore W4284977495C38652104 @default.
• W4284977495 hasConceptScore W4284977495C41008148 @default.
• W4284977495 hasConceptScore W4284977495C67388219 @default.
• W4284977495 hasConceptScore W4284977495C71139939 @default.
• W4284977495 hasConceptScore W4284977495C99138194 @default.
• W4284977495 hasFunder F4320321001 @default.
• W4284977495 hasFunder F4320322665 @default.
• W4284977495 hasFunder F4320322687 @default.
• W4284977495 hasFunder F4320323172 @default.
• W4284977495 hasLocation W42849774951 @default.
• W4284977495 hasOpenAccess W4284977495 @default.
• W4284977495 hasPrimaryLocation W42849774951 @default.
• W4284977495 hasRelatedWork W1999265394 @default.
• W4284977495 hasRelatedWork W2607231852 @default.
• W4284977495 hasRelatedWork W2618124519 @default.
• W4284977495 hasRelatedWork W3087964089 @default.
• W4284977495 hasRelatedWork W3099385964 @default.
• W4284977495 hasRelatedWork W3158263601 @default.
• W4284977495 hasRelatedWork W3160969343 @default.
• W4284977495 hasRelatedWork W4285484072 @default.
• W4284977495 hasRelatedWork W4312454624 @default.
• W4284977495 hasRelatedWork W4376852433 @default.
• W4284977495 hasVolume "608" @default.
• W4284977495 isParatext "false" @default.

• next