Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899496144> ?p ?o ?g. }
- W2899496144 endingPage "67188" @default.
- W2899496144 startingPage "67176" @default.
- W2899496144 abstract "The selection of semantic concepts for modal construction and data collection remains an open research issue. It is highly demanding to choose good multimedia concepts with small semantic gaps to facilitate the work of cross-media system developers. However, very little work has been done in this area. This paper contributes a new, real-world web image dataset for cross-media retrieval called FB5K. The proposed FB5K dataset contains the following attributes: 1) 5130 images crawled from Facebook; 2) images that are categorized according to users’ feelings; 3) images independent of text and language rather than using feelings for search. Furthermore, we propose a novel approach through the use of Optical Character Recognition and explicit incorporation of high-level semantic information. We comprehensively compute the performance of four different subspace-learning methods and three modified versions of the Correspondence Auto Encoder, alongside numerous text features and similarity measurements comparing Wikipedia, Flickr30k, and FB5K. To check the characteristics of FB5K, we propose a semantic-based cross-media retrieval method. To accomplish cross-media retrieval, we introduced a new similarity measurement in the embedded space, which significantly improved system performance compared with the conventional Euclidean distance. Our experimental results demonstrated the efficiency of the proposed retrieval method on three different datasets to simplify and improve general image retrieval." @default.
- W2899496144 created "2018-11-09" @default.
- W2899496144 creator A5035979541 @default.
- W2899496144 creator A5040007583 @default.
- W2899496144 creator A5048394282 @default.
- W2899496144 creator A5083181758 @default.
- W2899496144 date "2018-01-01" @default.
- W2899496144 modified "2023-10-14" @default.
- W2899496144 title "A Benchmark Dataset and Learning High-Level Semantic Embeddings of Multimedia for Cross-Media Retrieval" @default.
- W2899496144 cites W1501531539 @default.
- W2899496144 cites W1566135517 @default.
- W2899496144 cites W1596649971 @default.
- W2899496144 cites W1949478088 @default.
- W2899496144 cites W1964073652 @default.
- W2899496144 cites W1988423806 @default.
- W2899496144 cites W2007972815 @default.
- W2899496144 cites W2013535308 @default.
- W2899496144 cites W2019863495 @default.
- W2899496144 cites W2031332477 @default.
- W2899496144 cites W2042969131 @default.
- W2899496144 cites W2052727801 @default.
- W2899496144 cites W2053571848 @default.
- W2899496144 cites W2053946370 @default.
- W2899496144 cites W2070753207 @default.
- W2899496144 cites W2071051349 @default.
- W2899496144 cites W2071207147 @default.
- W2899496144 cites W2083790821 @default.
- W2899496144 cites W2087544865 @default.
- W2899496144 cites W2089720846 @default.
- W2899496144 cites W2090575037 @default.
- W2899496144 cites W2100235303 @default.
- W2899496144 cites W2106277773 @default.
- W2899496144 cites W2106732680 @default.
- W2899496144 cites W2110764733 @default.
- W2899496144 cites W2112193096 @default.
- W2899496144 cites W2125238156 @default.
- W2899496144 cites W2137225583 @default.
- W2899496144 cites W2138118304 @default.
- W2899496144 cites W2141282920 @default.
- W2899496144 cites W2151103935 @default.
- W2899496144 cites W2155893237 @default.
- W2899496144 cites W2161969291 @default.
- W2899496144 cites W2165072487 @default.
- W2899496144 cites W2165430451 @default.
- W2899496144 cites W2185175083 @default.
- W2899496144 cites W2210322478 @default.
- W2899496144 cites W2217869562 @default.
- W2899496144 cites W2294512729 @default.
- W2899496144 cites W2326180695 @default.
- W2899496144 cites W2337005149 @default.
- W2899496144 cites W2342543219 @default.
- W2899496144 cites W2474574787 @default.
- W2899496144 cites W2518029102 @default.
- W2899496144 cites W2538394767 @default.
- W2899496144 cites W2565217611 @default.
- W2899496144 cites W2600067905 @default.
- W2899496144 cites W2606965845 @default.
- W2899496144 cites W2743106775 @default.
- W2899496144 cites W2781877551 @default.
- W2899496144 cites W2786509977 @default.
- W2899496144 cites W2963996300 @default.
- W2899496144 cites W3098232083 @default.
- W2899496144 cites W68733909 @default.
- W2899496144 doi "https://doi.org/10.1109/access.2018.2878868" @default.
- W2899496144 hasPublicationYear "2018" @default.
- W2899496144 type Work @default.
- W2899496144 sameAs 2899496144 @default.
- W2899496144 citedByCount "20" @default.
- W2899496144 countsByYear W28994961442019 @default.
- W2899496144 countsByYear W28994961442020 @default.
- W2899496144 countsByYear W28994961442021 @default.
- W2899496144 countsByYear W28994961442022 @default.
- W2899496144 countsByYear W28994961442023 @default.
- W2899496144 crossrefType "journal-article" @default.
- W2899496144 hasAuthorship W2899496144A5035979541 @default.
- W2899496144 hasAuthorship W2899496144A5040007583 @default.
- W2899496144 hasAuthorship W2899496144A5048394282 @default.
- W2899496144 hasAuthorship W2899496144A5083181758 @default.
- W2899496144 hasBestOaLocation W28994961441 @default.
- W2899496144 hasConcept C103278499 @default.
- W2899496144 hasConcept C111919701 @default.
- W2899496144 hasConcept C115961682 @default.
- W2899496144 hasConcept C118505674 @default.
- W2899496144 hasConcept C130318100 @default.
- W2899496144 hasConcept C13280743 @default.
- W2899496144 hasConcept C154945302 @default.
- W2899496144 hasConcept C1667742 @default.
- W2899496144 hasConcept C173862523 @default.
- W2899496144 hasConcept C185798385 @default.
- W2899496144 hasConcept C205649164 @default.
- W2899496144 hasConcept C2129575 @default.
- W2899496144 hasConcept C23123220 @default.
- W2899496144 hasConcept C2776318140 @default.
- W2899496144 hasConcept C32834561 @default.
- W2899496144 hasConcept C41008148 @default.
- W2899496144 hasConcept C511149849 @default.
- W2899496144 hasConcept C6881194 @default.
- W2899496144 hasConceptScore W2899496144C103278499 @default.