Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293202987> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4293202987 endingPage "1" @default.
- W4293202987 startingPage "1" @default.
- W4293202987 abstract "Speech-image retrieval aims at learning the relevance between image and speech. Prior approaches are mainly based on bi-modal contrastive learning, which can not alleviate the cross-modal heterogeneous issue between visual and acoustic modalities well. To address this issue, we propose a visual-acoustic-semantic embedding (VASE) method. First, we propose a tri-modal ranking loss by taking advantage of semantic information corresponding to the acoustic data, which introduces the auxiliary alignment to enhance the alignment between image and speech. Second, we introduce a cycle-consistency loss based on feature reconstruction. It can further alleviate the heterogeneous issue between different data modalities (e.g., visual-acoustic, visual-textual and acoustic-textual). Extensive experiments have demonstrated the effectiveness of our proposed method. In addition, our VASE model achieves state-of-the-art performance on the speech-image retrieval task on the Flickr8K [4] and Places [2] datasets." @default.
- W4293202987 created "2022-08-27" @default.
- W4293202987 creator A5013506657 @default.
- W4293202987 creator A5013541187 @default.
- W4293202987 creator A5055653308 @default.
- W4293202987 creator A5085690911 @default.
- W4293202987 creator A5086664647 @default.
- W4293202987 date "2022-01-01" @default.
- W4293202987 modified "2023-10-15" @default.
- W4293202987 title "A Reconstruction-based Visual-Acoustic-Semantic Embedding Method for Speech-Image Retrieval" @default.
- W4293202987 doi "https://doi.org/10.1109/tmm.2022.3171090" @default.
- W4293202987 hasPublicationYear "2022" @default.
- W4293202987 type Work @default.
- W4293202987 citedByCount "0" @default.
- W4293202987 crossrefType "journal-article" @default.
- W4293202987 hasAuthorship W4293202987A5013506657 @default.
- W4293202987 hasAuthorship W4293202987A5013541187 @default.
- W4293202987 hasAuthorship W4293202987A5055653308 @default.
- W4293202987 hasAuthorship W4293202987A5085690911 @default.
- W4293202987 hasAuthorship W4293202987A5086664647 @default.
- W4293202987 hasConcept C115961682 @default.
- W4293202987 hasConcept C138885662 @default.
- W4293202987 hasConcept C154945302 @default.
- W4293202987 hasConcept C158154518 @default.
- W4293202987 hasConcept C1667742 @default.
- W4293202987 hasConcept C17744445 @default.
- W4293202987 hasConcept C189430467 @default.
- W4293202987 hasConcept C199539241 @default.
- W4293202987 hasConcept C204321447 @default.
- W4293202987 hasConcept C2776401178 @default.
- W4293202987 hasConcept C2780226545 @default.
- W4293202987 hasConcept C28490314 @default.
- W4293202987 hasConcept C41008148 @default.
- W4293202987 hasConcept C41608201 @default.
- W4293202987 hasConcept C41895202 @default.
- W4293202987 hasConceptScore W4293202987C115961682 @default.
- W4293202987 hasConceptScore W4293202987C138885662 @default.
- W4293202987 hasConceptScore W4293202987C154945302 @default.
- W4293202987 hasConceptScore W4293202987C158154518 @default.
- W4293202987 hasConceptScore W4293202987C1667742 @default.
- W4293202987 hasConceptScore W4293202987C17744445 @default.
- W4293202987 hasConceptScore W4293202987C189430467 @default.
- W4293202987 hasConceptScore W4293202987C199539241 @default.
- W4293202987 hasConceptScore W4293202987C204321447 @default.
- W4293202987 hasConceptScore W4293202987C2776401178 @default.
- W4293202987 hasConceptScore W4293202987C2780226545 @default.
- W4293202987 hasConceptScore W4293202987C28490314 @default.
- W4293202987 hasConceptScore W4293202987C41008148 @default.
- W4293202987 hasConceptScore W4293202987C41608201 @default.
- W4293202987 hasConceptScore W4293202987C41895202 @default.
- W4293202987 hasFunder F4320321001 @default.
- W4293202987 hasFunder F4320334978 @default.
- W4293202987 hasLocation W42932029871 @default.
- W4293202987 hasOpenAccess W4293202987 @default.
- W4293202987 hasPrimaryLocation W42932029871 @default.
- W4293202987 hasRelatedWork W2014421026 @default.
- W4293202987 hasRelatedWork W2021689839 @default.
- W4293202987 hasRelatedWork W2088097596 @default.
- W4293202987 hasRelatedWork W2116442280 @default.
- W4293202987 hasRelatedWork W2122909822 @default.
- W4293202987 hasRelatedWork W2808503949 @default.
- W4293202987 hasRelatedWork W2964189431 @default.
- W4293202987 hasRelatedWork W2972463063 @default.
- W4293202987 hasRelatedWork W2987958590 @default.
- W4293202987 hasRelatedWork W2997403743 @default.
- W4293202987 isParatext "false" @default.
- W4293202987 isRetracted "false" @default.
- W4293202987 workType "article" @default.