Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964276596> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2964276596 abstract "Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic relationships. Such a multi-modal embedding can be trained and used for various tasks, notably image captioning. In the present work, we introduce a new architecture of this type, with a visual path that leverages recent space-aware pooling mechanisms. Combined with a textual path which is jointly trained from scratch, our semantic-visual embedding offers a versatile model. Once trained under the supervision of captioned images, it yields new state-of-the-art performance on cross-modal retrieval. It also allows the localization of new concepts from the embedding space into any input image, delivering state-of-the-art result on the visual grounding of phrases." @default.
- W2964276596 created "2019-07-30" @default.
- W2964276596 creator A5022871131 @default.
- W2964276596 creator A5027039225 @default.
- W2964276596 creator A5052035887 @default.
- W2964276596 creator A5076170578 @default.
- W2964276596 date "2018-06-01" @default.
- W2964276596 modified "2023-10-13" @default.
- W2964276596 title "Finding Beans in Burgers: Deep Semantic-Visual Embedding with Localization" @default.
- W2964276596 cites W1832693441 @default.
- W2964276596 cites W1905882502 @default.
- W2964276596 cites W1916445035 @default.
- W2964276596 cites W1949478088 @default.
- W2964276596 cites W2025341678 @default.
- W2964276596 cites W2048110836 @default.
- W2964276596 cites W2064675550 @default.
- W2964276596 cites W2129156852 @default.
- W2964276596 cites W2130055251 @default.
- W2964276596 cites W2194775991 @default.
- W2964276596 cites W2250539671 @default.
- W2964276596 cites W2295107390 @default.
- W2964276596 cites W2438305798 @default.
- W2964276596 cites W2546696630 @default.
- W2964276596 cites W2737041163 @default.
- W2964276596 cites W2738853914 @default.
- W2964276596 cites W2778940641 @default.
- W2964276596 cites W2962858109 @default.
- W2964276596 cites W2963040148 @default.
- W2964276596 cites W2963042258 @default.
- W2964276596 cites W2963389687 @default.
- W2964276596 doi "https://doi.org/10.1109/cvpr.2018.00419" @default.
- W2964276596 hasPublicationYear "2018" @default.
- W2964276596 type Work @default.
- W2964276596 sameAs 2964276596 @default.
- W2964276596 citedByCount "65" @default.
- W2964276596 countsByYear W29642765962018 @default.
- W2964276596 countsByYear W29642765962019 @default.
- W2964276596 countsByYear W29642765962020 @default.
- W2964276596 countsByYear W29642765962021 @default.
- W2964276596 countsByYear W29642765962022 @default.
- W2964276596 countsByYear W29642765962023 @default.
- W2964276596 crossrefType "proceedings-article" @default.
- W2964276596 hasAuthorship W2964276596A5022871131 @default.
- W2964276596 hasAuthorship W2964276596A5027039225 @default.
- W2964276596 hasAuthorship W2964276596A5052035887 @default.
- W2964276596 hasAuthorship W2964276596A5076170578 @default.
- W2964276596 hasBestOaLocation W29642765962 @default.
- W2964276596 hasConcept C111919701 @default.
- W2964276596 hasConcept C115961682 @default.
- W2964276596 hasConcept C154945302 @default.
- W2964276596 hasConcept C157657479 @default.
- W2964276596 hasConcept C185592680 @default.
- W2964276596 hasConcept C188027245 @default.
- W2964276596 hasConcept C199360897 @default.
- W2964276596 hasConcept C2777735758 @default.
- W2964276596 hasConcept C2778572836 @default.
- W2964276596 hasConcept C2986420190 @default.
- W2964276596 hasConcept C31972630 @default.
- W2964276596 hasConcept C36464697 @default.
- W2964276596 hasConcept C41008148 @default.
- W2964276596 hasConcept C41608201 @default.
- W2964276596 hasConcept C70437156 @default.
- W2964276596 hasConcept C71139939 @default.
- W2964276596 hasConceptScore W2964276596C111919701 @default.
- W2964276596 hasConceptScore W2964276596C115961682 @default.
- W2964276596 hasConceptScore W2964276596C154945302 @default.
- W2964276596 hasConceptScore W2964276596C157657479 @default.
- W2964276596 hasConceptScore W2964276596C185592680 @default.
- W2964276596 hasConceptScore W2964276596C188027245 @default.
- W2964276596 hasConceptScore W2964276596C199360897 @default.
- W2964276596 hasConceptScore W2964276596C2777735758 @default.
- W2964276596 hasConceptScore W2964276596C2778572836 @default.
- W2964276596 hasConceptScore W2964276596C2986420190 @default.
- W2964276596 hasConceptScore W2964276596C31972630 @default.
- W2964276596 hasConceptScore W2964276596C36464697 @default.
- W2964276596 hasConceptScore W2964276596C41008148 @default.
- W2964276596 hasConceptScore W2964276596C41608201 @default.
- W2964276596 hasConceptScore W2964276596C70437156 @default.
- W2964276596 hasConceptScore W2964276596C71139939 @default.
- W2964276596 hasLocation W29642765961 @default.
- W2964276596 hasLocation W29642765962 @default.
- W2964276596 hasLocation W29642765963 @default.
- W2964276596 hasLocation W29642765964 @default.
- W2964276596 hasOpenAccess W2964276596 @default.
- W2964276596 hasPrimaryLocation W29642765961 @default.
- W2964276596 hasRelatedWork W2130228941 @default.
- W2964276596 hasRelatedWork W2161229648 @default.
- W2964276596 hasRelatedWork W2255924030 @default.
- W2964276596 hasRelatedWork W2795434624 @default.
- W2964276596 hasRelatedWork W2912415363 @default.
- W2964276596 hasRelatedWork W2945836425 @default.
- W2964276596 hasRelatedWork W2964276596 @default.
- W2964276596 hasRelatedWork W2993674027 @default.
- W2964276596 hasRelatedWork W4301259870 @default.
- W2964276596 hasRelatedWork W4320016117 @default.
- W2964276596 isParatext "false" @default.
- W2964276596 isRetracted "false" @default.
- W2964276596 magId "2964276596" @default.
- W2964276596 workType "article" @default.