FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953037339> ?p ?o ?g. }

• W2953037339 endingPage "187" @default.
• W2953037339 startingPage "174" @default.
• W2953037339 abstract "Cross-modal hashing aims to map heterogeneous cross-modal data into a common Hamming space, which can realize fast and flexible retrieval across different modalities. Unsupervised cross-modal hashing is more flexible and applicable than supervised methods, since no intensive labeling work is involved. However, existing unsupervised methods learn the hashing functions by preserving inter- and intra-correlations while ignoring the underlying manifold structure across different modalities, which is extremely helpful in capturing the meaningful nearest neighbors of different modalities for cross-modal retrieval. Furthermore, existing works mainly focus on pairwise relation modeling while ignoring the correlations within multiple modalities. To address the above-mentioned problems, in this paper, we propose a multi-pathwaygenerativeadversarialhashing approach for unsupervised cross-modal retrieval, which makes full use of a generative adversarial network's ability for unsupervised representation learning to exploit the underlying manifold structure of cross-modal data. The main contributions can be summarized as follows: First, we propose a multi-pathwaygenerativeadversarialnetwork to model cross-modal hashing in an unsupervised fashion. In the proposed network, given the data of one modality, the generative model tries to fit the distribution over the manifold structure and selects informative data of other modalities to challenge the discriminative model. The discriminative model learns to distinguish the generated data and the true positive data sampled from the correlation graph to achieve better retrieval accuracy. These two models are trained in an adversarial way to improve each other and promote hashing function learning. Second, we propose a correlation graph-based approach to capture the underlying manifold structure across different modalities so that data of different modalities but within the same manifold can have a smaller Hamming distance to promote retrieval accuracy. Extensive experiments compared with state-of-the-art methods on three widely used datasets verify the effectiveness of our proposed approach." @default.
• W2953037339 created "2019-06-27" @default.
• W2953037339 creator A5047811387 @default.
• W2953037339 creator A5057209439 @default.
• W2953037339 date "2020-01-01" @default.
• W2953037339 modified "2023-10-16" @default.
• W2953037339 title "Multi-Pathway Generative Adversarial Hashing for Unsupervised Cross-Modal Retrieval" @default.
• W2953037339 cites W1489116628 @default.
• W2953037339 cites W1522734439 @default.
• W2953037339 cites W1922199343 @default.
• W2953037339 cites W1939575207 @default.
• W2953037339 cites W1970055505 @default.
• W2953037339 cites W1979644923 @default.
• W2953037339 cites W2007972815 @default.
• W2953037339 cites W2016053056 @default.
• W2953037339 cites W2021122545 @default.
• W2953037339 cites W2044195942 @default.
• W2953037339 cites W2049993534 @default.
• W2953037339 cites W2051666324 @default.
• W2953037339 cites W2057228822 @default.
• W2953037339 cites W2086958058 @default.
• W2953037339 cites W2093091163 @default.
• W2953037339 cites W2100235303 @default.
• W2953037339 cites W2155803963 @default.
• W2953037339 cites W2266728343 @default.
• W2953037339 cites W2295151578 @default.
• W2953037339 cites W2342543219 @default.
• W2953037339 cites W2388114291 @default.
• W2953037339 cites W2418353079 @default.
• W2953037339 cites W2493727926 @default.
• W2953037339 cites W2512032049 @default.
• W2953037339 cites W2584535601 @default.
• W2953037339 cites W2606965845 @default.
• W2953037339 cites W2618530766 @default.
• W2953037339 cites W2625219738 @default.
• W2953037339 cites W2741168003 @default.
• W2953037339 cites W2752930373 @default.
• W2953037339 cites W2765440071 @default.
• W2953037339 cites W2791083848 @default.
• W2953037339 cites W2795832645 @default.
• W2953037339 cites W2807548702 @default.
• W2953037339 cites W2808282156 @default.
• W2953037339 cites W2907166662 @default.
• W2953037339 cites W2919115771 @default.
• W2953037339 cites W2963213486 @default.
• W2953037339 cites W3098232083 @default.
• W2953037339 cites W3101023724 @default.
• W2953037339 doi "https://doi.org/10.1109/tmm.2019.2922128" @default.
• W2953037339 hasPublicationYear "2020" @default.
• W2953037339 type Work @default.
• W2953037339 sameAs 2953037339 @default.
• W2953037339 citedByCount "58" @default.
• W2953037339 countsByYear W29530373392019 @default.
• W2953037339 countsByYear W29530373392020 @default.
• W2953037339 countsByYear W29530373392021 @default.
• W2953037339 countsByYear W29530373392022 @default.
• W2953037339 countsByYear W29530373392023 @default.
• W2953037339 crossrefType "journal-article" @default.
• W2953037339 hasAuthorship W2953037339A5047811387 @default.
• W2953037339 hasAuthorship W2953037339A5057209439 @default.
• W2953037339 hasConcept C119857082 @default.
• W2953037339 hasConcept C132525143 @default.
• W2953037339 hasConcept C153180895 @default.
• W2953037339 hasConcept C154945302 @default.
• W2953037339 hasConcept C167966045 @default.
• W2953037339 hasConcept C184898388 @default.
• W2953037339 hasConcept C185592680 @default.
• W2953037339 hasConcept C188027245 @default.
• W2953037339 hasConcept C38652104 @default.
• W2953037339 hasConcept C39890363 @default.
• W2953037339 hasConcept C41008148 @default.
• W2953037339 hasConcept C59404180 @default.
• W2953037339 hasConcept C71139939 @default.
• W2953037339 hasConcept C8038995 @default.
• W2953037339 hasConcept C80444323 @default.
• W2953037339 hasConcept C97931131 @default.
• W2953037339 hasConcept C99138194 @default.
• W2953037339 hasConceptScore W2953037339C119857082 @default.
• W2953037339 hasConceptScore W2953037339C132525143 @default.
• W2953037339 hasConceptScore W2953037339C153180895 @default.
• W2953037339 hasConceptScore W2953037339C154945302 @default.
• W2953037339 hasConceptScore W2953037339C167966045 @default.
• W2953037339 hasConceptScore W2953037339C184898388 @default.
• W2953037339 hasConceptScore W2953037339C185592680 @default.
• W2953037339 hasConceptScore W2953037339C188027245 @default.
• W2953037339 hasConceptScore W2953037339C38652104 @default.
• W2953037339 hasConceptScore W2953037339C39890363 @default.
• W2953037339 hasConceptScore W2953037339C41008148 @default.
• W2953037339 hasConceptScore W2953037339C59404180 @default.
• W2953037339 hasConceptScore W2953037339C71139939 @default.
• W2953037339 hasConceptScore W2953037339C8038995 @default.
• W2953037339 hasConceptScore W2953037339C80444323 @default.
• W2953037339 hasConceptScore W2953037339C97931131 @default.
• W2953037339 hasConceptScore W2953037339C99138194 @default.
• W2953037339 hasFunder F4320321001 @default.
• W2953037339 hasIssue "1" @default.
• W2953037339 hasLocation W29530373391 @default.
• W2953037339 hasOpenAccess W2953037339 @default.

• next