Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033740891> ?p ?o ?g. }
- W3033740891 endingPage "1851" @default.
- W3033740891 startingPage "1838" @default.
- W3033740891 abstract "Hashing has been widely applied to multimodal retrieval on large-scale multimedia data due to its efficiency in computation and storage. In this article, we propose a novel deep semantic multimodal hashing network (DSMHN) for scalable image-text and video-text retrieval. The proposed deep hashing framework leverages 2-D convolutional neural networks (CNN) as the backbone network to capture the spatial information for image-text retrieval, while the 3-D CNN as the backbone network to capture the spatial and temporal information for video-text retrieval. In the DSMHN, two sets of modality-specific hash functions are jointly learned by explicitly preserving both intermodality similarities and intramodality semantic labels. Specifically, with the assumption that the learned hash codes should be optimal for the classification task, two stream networks are jointly trained to learn the hash functions by embedding the semantic labels on the resultant hash codes. Moreover, a unified deep multimodal hashing framework is proposed to learn compact and high-quality hash codes by exploiting the feature representation learning, intermodality similarity-preserving learning, semantic label-preserving learning, and hash function learning with different types of loss functions simultaneously. The proposed DSMHN method is a generic and scalable deep hashing framework for both image-text and video-text retrievals, which can be flexibly integrated with different types of loss functions. We conduct extensive experiments for both single-modal- and cross-modal-retrieval tasks on four widely used multimodal-retrieval data sets. Experimental results on both image-text- and video-text-retrieval tasks demonstrate that the DSMHN significantly outperforms the state-of-the-art methods." @default.
- W3033740891 created "2020-06-12" @default.
- W3033740891 creator A5017096005 @default.
- W3033740891 creator A5035112538 @default.
- W3033740891 creator A5076666788 @default.
- W3033740891 date "2023-04-01" @default.
- W3033740891 modified "2023-10-17" @default.
- W3033740891 title "Deep Semantic Multimodal Hashing Network for Scalable Image-Text and Video-Text Retrievals" @default.
- W3033740891 cites W1745334888 @default.
- W3033740891 cites W1895577753 @default.
- W3033740891 cites W1922199343 @default.
- W3033740891 cites W1939575207 @default.
- W3033740891 cites W1956333070 @default.
- W3033740891 cites W1970055505 @default.
- W3033740891 cites W1976258951 @default.
- W3033740891 cites W1985436611 @default.
- W3033740891 cites W1997107867 @default.
- W3033740891 cites W2007972815 @default.
- W3033740891 cites W2016053056 @default.
- W3033740891 cites W2049993534 @default.
- W3033740891 cites W2062118960 @default.
- W3033740891 cites W2084363474 @default.
- W3033740891 cites W2086958058 @default.
- W3033740891 cites W2087193308 @default.
- W3033740891 cites W2097117768 @default.
- W3033740891 cites W2106277773 @default.
- W3033740891 cites W2123229215 @default.
- W3033740891 cites W2138118304 @default.
- W3033740891 cites W2147717514 @default.
- W3033740891 cites W2159373756 @default.
- W3033740891 cites W2183341477 @default.
- W3033740891 cites W2199369932 @default.
- W3033740891 cites W2203543769 @default.
- W3033740891 cites W2266728343 @default.
- W3033740891 cites W2293824885 @default.
- W3033740891 cites W2326180695 @default.
- W3033740891 cites W2345649690 @default.
- W3033740891 cites W2388114291 @default.
- W3033740891 cites W2425121537 @default.
- W3033740891 cites W2425857666 @default.
- W3033740891 cites W2464915613 @default.
- W3033740891 cites W2499468060 @default.
- W3033740891 cites W2509619282 @default.
- W3033740891 cites W2550553598 @default.
- W3033740891 cites W2565611351 @default.
- W3033740891 cites W2570189907 @default.
- W3033740891 cites W2586937979 @default.
- W3033740891 cites W2594227027 @default.
- W3033740891 cites W2602143720 @default.
- W3033740891 cites W2619170298 @default.
- W3033740891 cites W2624945720 @default.
- W3033740891 cites W2736503945 @default.
- W3033740891 cites W2739103128 @default.
- W3033740891 cites W2739130108 @default.
- W3033740891 cites W2768428796 @default.
- W3033740891 cites W2772756366 @default.
- W3033740891 cites W2781821509 @default.
- W3033740891 cites W2798956329 @default.
- W3033740891 cites W2799245683 @default.
- W3033740891 cites W2801086478 @default.
- W3033740891 cites W2801765193 @default.
- W3033740891 cites W2809153957 @default.
- W3033740891 cites W2832876791 @default.
- W3033740891 cites W2894874917 @default.
- W3033740891 cites W2894879246 @default.
- W3033740891 cites W2895249671 @default.
- W3033740891 cites W2914578055 @default.
- W3033740891 cites W2919115771 @default.
- W3033740891 cites W2949049896 @default.
- W3033740891 cites W2962786441 @default.
- W3033740891 cites W2963150697 @default.
- W3033740891 cites W2963187862 @default.
- W3033740891 cites W2963524571 @default.
- W3033740891 cites W2964158883 @default.
- W3033740891 cites W3025665229 @default.
- W3033740891 doi "https://doi.org/10.1109/tnnls.2020.2997020" @default.
- W3033740891 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32502968" @default.
- W3033740891 hasPublicationYear "2023" @default.
- W3033740891 type Work @default.
- W3033740891 sameAs 3033740891 @default.
- W3033740891 citedByCount "36" @default.
- W3033740891 countsByYear W30337408912020 @default.
- W3033740891 countsByYear W30337408912021 @default.
- W3033740891 countsByYear W30337408912022 @default.
- W3033740891 countsByYear W30337408912023 @default.
- W3033740891 crossrefType "journal-article" @default.
- W3033740891 hasAuthorship W3033740891A5017096005 @default.
- W3033740891 hasAuthorship W3033740891A5035112538 @default.
- W3033740891 hasAuthorship W3033740891A5076666788 @default.
- W3033740891 hasBestOaLocation W30337408912 @default.
- W3033740891 hasConcept C108583219 @default.
- W3033740891 hasConcept C115961682 @default.
- W3033740891 hasConcept C122907437 @default.
- W3033740891 hasConcept C130318100 @default.
- W3033740891 hasConcept C133667856 @default.
- W3033740891 hasConcept C138111711 @default.
- W3033740891 hasConcept C153180895 @default.
- W3033740891 hasConcept C154945302 @default.