Matches in SemOpenAlex for { <https://semopenalex.org/work/W3160339728> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3160339728 abstract "Due to the high cost of large-scale strong labeling, sound event detection (SED) using only weakly-labeled and unlabeled data has drawn increasing attention in recent years. To exploit large amount of unlabeled in-domain data efficiently, we applied three semi-supervised learning strategies: interpolation consistency training (ICT), shift consistency training (SCT), and weakly pseudo-labeling. In addition, we propose FP-CRNN, a convolutional recurrent neural network (CRNN) which contains feature-pyramid (FP) components, to leverage temporal information by utilizing features at different scales. Experiments were conducted on DCASE 2020 task 4. In terms of event-based F-measure, these approaches outperform the official baseline system, at 34.8%, with the highest F-measure of 48.0% achieved by an FP-CRNN that was trained with the combination of all three strategies." @default.
- W3160339728 created "2021-05-24" @default.
- W3160339728 creator A5042123107 @default.
- W3160339728 creator A5064820492 @default.
- W3160339728 creator A5067733680 @default.
- W3160339728 creator A5084266744 @default.
- W3160339728 date "2021-06-06" @default.
- W3160339728 modified "2023-10-14" @default.
- W3160339728 title "Sound Event Detection by Consistency Training and Pseudo-Labeling With Feature-Pyramid Convolutional Recurrent Neural Networks" @default.
- W3160339728 cites W2169138660 @default.
- W3160339728 cites W2194775991 @default.
- W3160339728 cites W2296193698 @default.
- W3160339728 cites W2565639579 @default.
- W3160339728 cites W2591013610 @default.
- W3160339728 cites W2746554716 @default.
- W3160339728 cites W2963543871 @default.
- W3160339728 cites W2963723765 @default.
- W3160339728 cites W2982623348 @default.
- W3160339728 cites W3006275583 @default.
- W3160339728 cites W3015190346 @default.
- W3160339728 cites W3209458476 @default.
- W3160339728 doi "https://doi.org/10.1109/icassp39728.2021.9414350" @default.
- W3160339728 hasPublicationYear "2021" @default.
- W3160339728 type Work @default.
- W3160339728 sameAs 3160339728 @default.
- W3160339728 citedByCount "13" @default.
- W3160339728 countsByYear W31603397282020 @default.
- W3160339728 countsByYear W31603397282022 @default.
- W3160339728 countsByYear W31603397282023 @default.
- W3160339728 crossrefType "proceedings-article" @default.
- W3160339728 hasAuthorship W3160339728A5042123107 @default.
- W3160339728 hasAuthorship W3160339728A5064820492 @default.
- W3160339728 hasAuthorship W3160339728A5067733680 @default.
- W3160339728 hasAuthorship W3160339728A5084266744 @default.
- W3160339728 hasConcept C138885662 @default.
- W3160339728 hasConcept C142575187 @default.
- W3160339728 hasConcept C147168706 @default.
- W3160339728 hasConcept C153083717 @default.
- W3160339728 hasConcept C153180895 @default.
- W3160339728 hasConcept C154945302 @default.
- W3160339728 hasConcept C2524010 @default.
- W3160339728 hasConcept C2776401178 @default.
- W3160339728 hasConcept C2776436953 @default.
- W3160339728 hasConcept C28490314 @default.
- W3160339728 hasConcept C33923547 @default.
- W3160339728 hasConcept C41008148 @default.
- W3160339728 hasConcept C41895202 @default.
- W3160339728 hasConcept C50644808 @default.
- W3160339728 hasConcept C81363708 @default.
- W3160339728 hasConceptScore W3160339728C138885662 @default.
- W3160339728 hasConceptScore W3160339728C142575187 @default.
- W3160339728 hasConceptScore W3160339728C147168706 @default.
- W3160339728 hasConceptScore W3160339728C153083717 @default.
- W3160339728 hasConceptScore W3160339728C153180895 @default.
- W3160339728 hasConceptScore W3160339728C154945302 @default.
- W3160339728 hasConceptScore W3160339728C2524010 @default.
- W3160339728 hasConceptScore W3160339728C2776401178 @default.
- W3160339728 hasConceptScore W3160339728C2776436953 @default.
- W3160339728 hasConceptScore W3160339728C28490314 @default.
- W3160339728 hasConceptScore W3160339728C33923547 @default.
- W3160339728 hasConceptScore W3160339728C41008148 @default.
- W3160339728 hasConceptScore W3160339728C41895202 @default.
- W3160339728 hasConceptScore W3160339728C50644808 @default.
- W3160339728 hasConceptScore W3160339728C81363708 @default.
- W3160339728 hasLocation W31603397281 @default.
- W3160339728 hasOpenAccess W3160339728 @default.
- W3160339728 hasPrimaryLocation W31603397281 @default.
- W3160339728 hasRelatedWork W2295021132 @default.
- W3160339728 hasRelatedWork W2546942002 @default.
- W3160339728 hasRelatedWork W2767651786 @default.
- W3160339728 hasRelatedWork W2886673456 @default.
- W3160339728 hasRelatedWork W2912288872 @default.
- W3160339728 hasRelatedWork W2970216048 @default.
- W3160339728 hasRelatedWork W3106036237 @default.
- W3160339728 hasRelatedWork W3148519004 @default.
- W3160339728 hasRelatedWork W564581980 @default.
- W3160339728 hasRelatedWork W785854688 @default.
- W3160339728 isParatext "false" @default.
- W3160339728 isRetracted "false" @default.
- W3160339728 magId "3160339728" @default.
- W3160339728 workType "article" @default.