Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204267711> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3204267711 abstract "We investigate unsupervised learning of correspondences between sound events and textual phrases through aligning audio clips with textual captions describing the content of a whole audio clip. We align originally unaligned and unannotated audio clips and their captions by scoring the similarities between audio frames and words, as encoded by modality-specific encoders and using a ranking-loss criterion to optimize the model. After training, we obtain clip-caption similarity by averaging frame-word similarities and estimate event-phrase correspondences by calculating frame-phrase similarities. We evaluate the method with two cross-modal tasks: audio-caption retrieval, and phrase-based sound event detection (SED). Experimental results show that the proposed method can globally associate audio clips with captions as well as locally learn correspondences between individual sound events and textual phrases in an unsupervised manner." @default.
- W3204267711 created "2021-10-11" @default.
- W3204267711 creator A5016518233 @default.
- W3204267711 creator A5036989493 @default.
- W3204267711 creator A5049691461 @default.
- W3204267711 creator A5087751248 @default.
- W3204267711 date "2022-05-23" @default.
- W3204267711 modified "2023-10-16" @default.
- W3204267711 title "Unsupervised Audio-Caption Aligning Learns Correspondences Between Individual Sound Events and Textual Phrases" @default.
- W3204267711 cites W2171590421 @default.
- W3204267711 cites W2619383789 @default.
- W3204267711 cites W2796315435 @default.
- W3204267711 cites W2940092410 @default.
- W3204267711 cites W2964213897 @default.
- W3204267711 cites W2965809241 @default.
- W3204267711 cites W2997525715 @default.
- W3204267711 cites W3005971801 @default.
- W3204267711 cites W3015591594 @default.
- W3204267711 cites W3044495139 @default.
- W3204267711 cites W3161204797 @default.
- W3204267711 cites W3163843406 @default.
- W3204267711 cites W3197467690 @default.
- W3204267711 doi "https://doi.org/10.1109/icassp43922.2022.9747336" @default.
- W3204267711 hasPublicationYear "2022" @default.
- W3204267711 type Work @default.
- W3204267711 sameAs 3204267711 @default.
- W3204267711 citedByCount "5" @default.
- W3204267711 countsByYear W32042677112022 @default.
- W3204267711 countsByYear W32042677112023 @default.
- W3204267711 crossrefType "proceedings-article" @default.
- W3204267711 hasAuthorship W3204267711A5016518233 @default.
- W3204267711 hasAuthorship W3204267711A5036989493 @default.
- W3204267711 hasAuthorship W3204267711A5049691461 @default.
- W3204267711 hasAuthorship W3204267711A5087751248 @default.
- W3204267711 hasBestOaLocation W32042677112 @default.
- W3204267711 hasConcept C103278499 @default.
- W3204267711 hasConcept C115961682 @default.
- W3204267711 hasConcept C121332964 @default.
- W3204267711 hasConcept C126042441 @default.
- W3204267711 hasConcept C138885662 @default.
- W3204267711 hasConcept C154945302 @default.
- W3204267711 hasConcept C204321447 @default.
- W3204267711 hasConcept C2776224158 @default.
- W3204267711 hasConcept C2778739407 @default.
- W3204267711 hasConcept C2779662365 @default.
- W3204267711 hasConcept C2780226545 @default.
- W3204267711 hasConcept C28490314 @default.
- W3204267711 hasConcept C41008148 @default.
- W3204267711 hasConcept C41895202 @default.
- W3204267711 hasConcept C62520636 @default.
- W3204267711 hasConcept C76155785 @default.
- W3204267711 hasConcept C90805587 @default.
- W3204267711 hasConceptScore W3204267711C103278499 @default.
- W3204267711 hasConceptScore W3204267711C115961682 @default.
- W3204267711 hasConceptScore W3204267711C121332964 @default.
- W3204267711 hasConceptScore W3204267711C126042441 @default.
- W3204267711 hasConceptScore W3204267711C138885662 @default.
- W3204267711 hasConceptScore W3204267711C154945302 @default.
- W3204267711 hasConceptScore W3204267711C204321447 @default.
- W3204267711 hasConceptScore W3204267711C2776224158 @default.
- W3204267711 hasConceptScore W3204267711C2778739407 @default.
- W3204267711 hasConceptScore W3204267711C2779662365 @default.
- W3204267711 hasConceptScore W3204267711C2780226545 @default.
- W3204267711 hasConceptScore W3204267711C28490314 @default.
- W3204267711 hasConceptScore W3204267711C41008148 @default.
- W3204267711 hasConceptScore W3204267711C41895202 @default.
- W3204267711 hasConceptScore W3204267711C62520636 @default.
- W3204267711 hasConceptScore W3204267711C76155785 @default.
- W3204267711 hasConceptScore W3204267711C90805587 @default.
- W3204267711 hasFunder F4320321108 @default.
- W3204267711 hasLocation W32042677111 @default.
- W3204267711 hasLocation W32042677112 @default.
- W3204267711 hasOpenAccess W3204267711 @default.
- W3204267711 hasPrimaryLocation W32042677111 @default.
- W3204267711 hasRelatedWork W1586984800 @default.
- W3204267711 hasRelatedWork W2019025599 @default.
- W3204267711 hasRelatedWork W2062849642 @default.
- W3204267711 hasRelatedWork W2100975566 @default.
- W3204267711 hasRelatedWork W2142990792 @default.
- W3204267711 hasRelatedWork W2348600475 @default.
- W3204267711 hasRelatedWork W2349125667 @default.
- W3204267711 hasRelatedWork W2785076216 @default.
- W3204267711 hasRelatedWork W3107474891 @default.
- W3204267711 hasRelatedWork W4255547271 @default.
- W3204267711 isParatext "false" @default.
- W3204267711 isRetracted "false" @default.
- W3204267711 magId "3204267711" @default.
- W3204267711 workType "article" @default.