Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783179304> ?p ?o ?g. }
- W2783179304 abstract "Recent advances in deep learning and distributed representations of images and text have resulted in the emergence of several neural architectures for cross-modal retrieval tasks, such as searching collections of images in response to textual queries and assigning textual descriptions to images. However, the multi-modal retrieval scenario, when a query can be either a text or an image and the goal is to retrieve both a textual fragment and an image, which should be considered as an atomic unit, has been significantly less studied. In this paper, we propose a gated neural architecture to project image and keyword queries as well as multi-modal retrieval units into the same low-dimensional embedding space and perform semantic matching in this space. The proposed architecture is trained to minimize structured hinge loss and can be applied to both cross- and multi-modal retrieval. Experimental results for six different cross- and multi-modal retrieval tasks obtained on publicly available datasets indicate superior retrieval accuracy of the proposed architecture in comparison to the state-of-art baselines." @default.
- W2783179304 created "2018-01-26" @default.
- W2783179304 creator A5025168533 @default.
- W2783179304 creator A5069560828 @default.
- W2783179304 date "2018-02-02" @default.
- W2783179304 modified "2023-10-18" @default.
- W2783179304 title "Deep Neural Architecture for Multi-Modal Retrieval based on Joint Embedding Space for Text and Images" @default.
- W2783179304 cites W1202352811 @default.
- W2783179304 cites W1905882502 @default.
- W2783179304 cites W1916445035 @default.
- W2783179304 cites W1931639407 @default.
- W2783179304 cites W1966443646 @default.
- W2783179304 cites W2007972815 @default.
- W2783179304 cites W2015175493 @default.
- W2783179304 cites W2017851434 @default.
- W2783179304 cites W2042980227 @default.
- W2783179304 cites W2055981215 @default.
- W2783179304 cites W2064675550 @default.
- W2783179304 cites W2068297964 @default.
- W2783179304 cites W2070753207 @default.
- W2783179304 cites W2093091163 @default.
- W2783179304 cites W2100235303 @default.
- W2783179304 cites W2102765684 @default.
- W2783179304 cites W2112796928 @default.
- W2783179304 cites W2117539524 @default.
- W2783179304 cites W2120526973 @default.
- W2783179304 cites W2131876387 @default.
- W2783179304 cites W2136189984 @default.
- W2783179304 cites W2183341477 @default.
- W2783179304 cites W2194775991 @default.
- W2783179304 cites W2250539671 @default.
- W2783179304 cites W2388114291 @default.
- W2783179304 cites W2463955103 @default.
- W2783179304 cites W2536015822 @default.
- W2783179304 cites W2537515450 @default.
- W2783179304 cites W2539671052 @default.
- W2783179304 cites W2568389463 @default.
- W2783179304 cites W2613589950 @default.
- W2783179304 cites W2740848765 @default.
- W2783179304 cites W29350917 @default.
- W2783179304 cites W2963389687 @default.
- W2783179304 cites W3000226596 @default.
- W2783179304 cites W3098232083 @default.
- W2783179304 cites W92662927 @default.
- W2783179304 doi "https://doi.org/10.1145/3159652.3159735" @default.
- W2783179304 hasPublicationYear "2018" @default.
- W2783179304 type Work @default.
- W2783179304 sameAs 2783179304 @default.
- W2783179304 citedByCount "13" @default.
- W2783179304 countsByYear W27831793042018 @default.
- W2783179304 countsByYear W27831793042019 @default.
- W2783179304 countsByYear W27831793042020 @default.
- W2783179304 countsByYear W27831793042021 @default.
- W2783179304 crossrefType "proceedings-article" @default.
- W2783179304 hasAuthorship W2783179304A5025168533 @default.
- W2783179304 hasAuthorship W2783179304A5069560828 @default.
- W2783179304 hasConcept C105795698 @default.
- W2783179304 hasConcept C111919701 @default.
- W2783179304 hasConcept C115961682 @default.
- W2783179304 hasConcept C123657996 @default.
- W2783179304 hasConcept C142362112 @default.
- W2783179304 hasConcept C153180895 @default.
- W2783179304 hasConcept C153349607 @default.
- W2783179304 hasConcept C154945302 @default.
- W2783179304 hasConcept C165064840 @default.
- W2783179304 hasConcept C1667742 @default.
- W2783179304 hasConcept C185592680 @default.
- W2783179304 hasConcept C188027245 @default.
- W2783179304 hasConcept C189391414 @default.
- W2783179304 hasConcept C23123220 @default.
- W2783179304 hasConcept C2778572836 @default.
- W2783179304 hasConcept C33923547 @default.
- W2783179304 hasConcept C41008148 @default.
- W2783179304 hasConcept C41608201 @default.
- W2783179304 hasConcept C71139939 @default.
- W2783179304 hasConceptScore W2783179304C105795698 @default.
- W2783179304 hasConceptScore W2783179304C111919701 @default.
- W2783179304 hasConceptScore W2783179304C115961682 @default.
- W2783179304 hasConceptScore W2783179304C123657996 @default.
- W2783179304 hasConceptScore W2783179304C142362112 @default.
- W2783179304 hasConceptScore W2783179304C153180895 @default.
- W2783179304 hasConceptScore W2783179304C153349607 @default.
- W2783179304 hasConceptScore W2783179304C154945302 @default.
- W2783179304 hasConceptScore W2783179304C165064840 @default.
- W2783179304 hasConceptScore W2783179304C1667742 @default.
- W2783179304 hasConceptScore W2783179304C185592680 @default.
- W2783179304 hasConceptScore W2783179304C188027245 @default.
- W2783179304 hasConceptScore W2783179304C189391414 @default.
- W2783179304 hasConceptScore W2783179304C23123220 @default.
- W2783179304 hasConceptScore W2783179304C2778572836 @default.
- W2783179304 hasConceptScore W2783179304C33923547 @default.
- W2783179304 hasConceptScore W2783179304C41008148 @default.
- W2783179304 hasConceptScore W2783179304C41608201 @default.
- W2783179304 hasConceptScore W2783179304C71139939 @default.
- W2783179304 hasLocation W27831793041 @default.
- W2783179304 hasOpenAccess W2783179304 @default.
- W2783179304 hasPrimaryLocation W27831793041 @default.
- W2783179304 hasRelatedWork W155590726 @default.
- W2783179304 hasRelatedWork W2011260834 @default.
- W2783179304 hasRelatedWork W2063218608 @default.