FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2959804535> ?p ?o ?g. }

• W2959804535 endingPage "2722" @default.
• W2959804535 startingPage "2709" @default.
• W2959804535 abstract "Multi-media data including image, video, text, audio, and 3D model, has been fast emerging on the Internet. Jointly correlating the data of various media types is a challenging task. With the considerable learning ability of deep network, existing works mainly construct multi-pathway network to learn cross-media correlation, where each pathway is for one media type. However, with number of media types increasing, existing methods face the problems of high repetition and complexity, leading to overfitting and poor generalization ability, which makes adverse effect on correlation learning. For addressing the above issues, we propose cross-media deep compression and regularization (CDCR) approach for quintuple-media joint correlation learning: 1) cross-media partial weight-sharing networks is proposed, where a part of parameters are commonly shared among multiple pathways, to exploit common characteristics across different media types for capturing intrinsic cross-media correlation; 2) we propose media-adaptive network pruning to drop connections between weakly-correlated neurons, which can emphasize media-specific characteristics adaptively; and 3) cross-media network regularization is proposed to utilize relationships among quintuple-media data, which can guarantee generalization ability and enhance intra-media and inter-media correlation. The experiments verify the effectiveness of our approach, which outperforms the state-of-the-art methods on two very challenging datasets, including a large-scale dataset PKU XMediaNet with more than 100 000 quintuple-media instances." @default.
• W2959804535 created "2019-07-23" @default.
• W2959804535 creator A5026142528 @default.
• W2959804535 creator A5047811387 @default.
• W2959804535 date "2020-08-01" @default.
• W2959804535 modified "2023-09-23" @default.
• W2959804535 title "Quintuple-Media Joint Correlation Learning With Deep Compression and Regularization" @default.
• W2959804535 cites W1123427201 @default.
• W2959804535 cites W1777628566 @default.
• W2959804535 cites W1832693441 @default.
• W2959804535 cites W1930223417 @default.
• W2959804535 cites W1949478088 @default.
• W2959804535 cites W1964073652 @default.
• W2959804535 cites W2013535308 @default.
• W2959804535 cites W2015394094 @default.
• W2959804535 cites W2021122545 @default.
• W2959804535 cites W2022398331 @default.
• W2959804535 cites W2052727801 @default.
• W2959804535 cites W2064675550 @default.
• W2959804535 cites W2070753207 @default.
• W2959804535 cites W2100235303 @default.
• W2959804535 cites W2106277773 @default.
• W2959804535 cites W2138118304 @default.
• W2959804535 cites W2152332944 @default.
• W2959804535 cites W2194775991 @default.
• W2959804535 cites W2210322478 @default.
• W2959804535 cites W2211092169 @default.
• W2959804535 cites W2316082076 @default.
• W2959804535 cites W2326180695 @default.
• W2959804535 cites W2342543219 @default.
• W2959804535 cites W2414522539 @default.
• W2959804535 cites W2469619714 @default.
• W2959804535 cites W2526479943 @default.
• W2959804535 cites W2546190447 @default.
• W2959804535 cites W2584535601 @default.
• W2959804535 cites W2605649771 @default.
• W2959804535 cites W2606965845 @default.
• W2959804535 cites W2750608840 @default.
• W2959804535 cites W2765440071 @default.
• W2959804535 cites W2899496144 @default.
• W2959804535 cites W2962805368 @default.
• W2959804535 cites W2963643655 @default.
• W2959804535 cites W2964081303 @default.
• W2959804535 cites W2964130424 @default.
• W2959804535 cites W4251308012 @default.
• W2959804535 doi "https://doi.org/10.1109/tcsvt.2019.2927295" @default.
• W2959804535 hasPublicationYear "2020" @default.
• W2959804535 type Work @default.
• W2959804535 sameAs 2959804535 @default.
• W2959804535 citedByCount "3" @default.
• W2959804535 countsByYear W29598045352021 @default.
• W2959804535 countsByYear W29598045352022 @default.
• W2959804535 crossrefType "journal-article" @default.
• W2959804535 hasAuthorship W2959804535A5026142528 @default.
• W2959804535 hasAuthorship W2959804535A5047811387 @default.
• W2959804535 hasConcept C108583219 @default.
• W2959804535 hasConcept C110875604 @default.
• W2959804535 hasConcept C117220453 @default.
• W2959804535 hasConcept C119857082 @default.
• W2959804535 hasConcept C136764020 @default.
• W2959804535 hasConcept C154945302 @default.
• W2959804535 hasConcept C162324750 @default.
• W2959804535 hasConcept C165696696 @default.
• W2959804535 hasConcept C187736073 @default.
• W2959804535 hasConcept C22019652 @default.
• W2959804535 hasConcept C2524010 @default.
• W2959804535 hasConcept C2776135515 @default.
• W2959804535 hasConcept C2780451532 @default.
• W2959804535 hasConcept C28006648 @default.
• W2959804535 hasConcept C33923547 @default.
• W2959804535 hasConcept C38652104 @default.
• W2959804535 hasConcept C41008148 @default.
• W2959804535 hasConcept C50644808 @default.
• W2959804535 hasConceptScore W2959804535C108583219 @default.
• W2959804535 hasConceptScore W2959804535C110875604 @default.
• W2959804535 hasConceptScore W2959804535C117220453 @default.
• W2959804535 hasConceptScore W2959804535C119857082 @default.
• W2959804535 hasConceptScore W2959804535C136764020 @default.
• W2959804535 hasConceptScore W2959804535C154945302 @default.
• W2959804535 hasConceptScore W2959804535C162324750 @default.
• W2959804535 hasConceptScore W2959804535C165696696 @default.
• W2959804535 hasConceptScore W2959804535C187736073 @default.
• W2959804535 hasConceptScore W2959804535C22019652 @default.
• W2959804535 hasConceptScore W2959804535C2524010 @default.
• W2959804535 hasConceptScore W2959804535C2776135515 @default.
• W2959804535 hasConceptScore W2959804535C2780451532 @default.
• W2959804535 hasConceptScore W2959804535C28006648 @default.
• W2959804535 hasConceptScore W2959804535C33923547 @default.
• W2959804535 hasConceptScore W2959804535C38652104 @default.
• W2959804535 hasConceptScore W2959804535C41008148 @default.
• W2959804535 hasConceptScore W2959804535C50644808 @default.
• W2959804535 hasFunder F4320321001 @default.
• W2959804535 hasIssue "8" @default.
• W2959804535 hasLocation W29598045351 @default.
• W2959804535 hasOpenAccess W2959804535 @default.
• W2959804535 hasPrimaryLocation W29598045351 @default.
• W2959804535 hasRelatedWork W2597787948 @default.
• W2959804535 hasRelatedWork W2964465226 @default.

• next