Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385265004> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4385265004 endingPage "517" @default.
- W4385265004 startingPage "502" @default.
- W4385265004 abstract "Many odontocetes produce whistles that feature characteristic contour shapes in spectrogram representations of their calls. Automatically extracting the time × frequency tracks of whistle contours has numerous subsequent applications, including species classification, identification, and density estimation. Deep-learning-based methods, which train models using analyst-annotated whistles, offer a promising way to reliably extract whistle contours. However, the application of such methods can be limited by the significant amount of time and labor required for analyst annotation. To overcome this challenge, a technique that learns from automatically generated pseudo-labels has been developed. These annotations are less accurate than those generated by human analysts but more cost-effective to generate. It is shown that standard training methods do not learn effective models from these pseudo-labels. An improved loss function designed to compensate for pseudo-label error that significantly increases whistle extraction performance is introduced. The experiments show that the developed technique performs well when trained with pseudo-labels generated by two different algorithms. Models trained with the generated pseudo-labels can extract whistles with an F1-score (the harmonic mean of precision and recall) of 86.31% and 87.2% for the two sets of pseudo-labels that are considered. This performance is competitive with a model trained with 12 539 expert-annotated whistles (F1-score of 87.47%)." @default.
- W4385265004 created "2023-07-27" @default.
- W4385265004 creator A5003841649 @default.
- W4385265004 creator A5017818989 @default.
- W4385265004 creator A5022008224 @default.
- W4385265004 creator A5071316406 @default.
- W4385265004 creator A5071643611 @default.
- W4385265004 date "2023-07-01" @default.
- W4385265004 modified "2023-09-28" @default.
- W4385265004 title "Using deep learning to track time × frequency whistle contours of toothed whales without human-annotated training data" @default.
- W4385265004 cites W1905677962 @default.
- W4385265004 cites W1977422643 @default.
- W4385265004 cites W1986327541 @default.
- W4385265004 cites W1986817693 @default.
- W4385265004 cites W1996416759 @default.
- W4385265004 cites W2024542481 @default.
- W4385265004 cites W2030965778 @default.
- W4385265004 cites W2045875322 @default.
- W4385265004 cites W2050345426 @default.
- W4385265004 cites W2075264811 @default.
- W4385265004 cites W2124346397 @default.
- W4385265004 cites W2147364008 @default.
- W4385265004 cites W2172812399 @default.
- W4385265004 cites W2519489905 @default.
- W4385265004 cites W2916994621 @default.
- W4385265004 cites W3042609801 @default.
- W4385265004 cites W3109630212 @default.
- W4385265004 cites W3124639793 @default.
- W4385265004 cites W4312207938 @default.
- W4385265004 doi "https://doi.org/10.1121/10.0020274" @default.
- W4385265004 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37493330" @default.
- W4385265004 hasPublicationYear "2023" @default.
- W4385265004 type Work @default.
- W4385265004 citedByCount "0" @default.
- W4385265004 crossrefType "journal-article" @default.
- W4385265004 hasAuthorship W4385265004A5003841649 @default.
- W4385265004 hasAuthorship W4385265004A5017818989 @default.
- W4385265004 hasAuthorship W4385265004A5022008224 @default.
- W4385265004 hasAuthorship W4385265004A5071316406 @default.
- W4385265004 hasAuthorship W4385265004A5071643611 @default.
- W4385265004 hasBestOaLocation W43852650041 @default.
- W4385265004 hasConcept C108583219 @default.
- W4385265004 hasConcept C116834253 @default.
- W4385265004 hasConcept C121332964 @default.
- W4385265004 hasConcept C138885662 @default.
- W4385265004 hasConcept C153180895 @default.
- W4385265004 hasConcept C153294291 @default.
- W4385265004 hasConcept C154945302 @default.
- W4385265004 hasConcept C2776321320 @default.
- W4385265004 hasConcept C2776401178 @default.
- W4385265004 hasConcept C2777211547 @default.
- W4385265004 hasConcept C28490314 @default.
- W4385265004 hasConcept C41008148 @default.
- W4385265004 hasConcept C41895202 @default.
- W4385265004 hasConcept C45273575 @default.
- W4385265004 hasConcept C59822182 @default.
- W4385265004 hasConcept C86803240 @default.
- W4385265004 hasConceptScore W4385265004C108583219 @default.
- W4385265004 hasConceptScore W4385265004C116834253 @default.
- W4385265004 hasConceptScore W4385265004C121332964 @default.
- W4385265004 hasConceptScore W4385265004C138885662 @default.
- W4385265004 hasConceptScore W4385265004C153180895 @default.
- W4385265004 hasConceptScore W4385265004C153294291 @default.
- W4385265004 hasConceptScore W4385265004C154945302 @default.
- W4385265004 hasConceptScore W4385265004C2776321320 @default.
- W4385265004 hasConceptScore W4385265004C2776401178 @default.
- W4385265004 hasConceptScore W4385265004C2777211547 @default.
- W4385265004 hasConceptScore W4385265004C28490314 @default.
- W4385265004 hasConceptScore W4385265004C41008148 @default.
- W4385265004 hasConceptScore W4385265004C41895202 @default.
- W4385265004 hasConceptScore W4385265004C45273575 @default.
- W4385265004 hasConceptScore W4385265004C59822182 @default.
- W4385265004 hasConceptScore W4385265004C86803240 @default.
- W4385265004 hasFunder F4320337345 @default.
- W4385265004 hasIssue "1" @default.
- W4385265004 hasLocation W43852650041 @default.
- W4385265004 hasLocation W43852650042 @default.
- W4385265004 hasOpenAccess W4385265004 @default.
- W4385265004 hasPrimaryLocation W43852650041 @default.
- W4385265004 hasRelatedWork W1529400504 @default.
- W4385265004 hasRelatedWork W1892467659 @default.
- W4385265004 hasRelatedWork W2382607599 @default.
- W4385265004 hasRelatedWork W2546942002 @default.
- W4385265004 hasRelatedWork W2731899572 @default.
- W4385265004 hasRelatedWork W2738221750 @default.
- W4385265004 hasRelatedWork W2897924318 @default.
- W4385265004 hasRelatedWork W2970216048 @default.
- W4385265004 hasRelatedWork W2973062255 @default.
- W4385265004 hasRelatedWork W3215138031 @default.
- W4385265004 hasVolume "154" @default.
- W4385265004 isParatext "false" @default.
- W4385265004 isRetracted "false" @default.
- W4385265004 workType "article" @default.