Matches in SemOpenAlex for { <https://semopenalex.org/work/W2758607890> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2758607890 abstract "Acoustic monitoring of bird species is an increasingly important field in signal processing. Many available bird sound datasets do not contain exact timestamp of the bird call but have a coarse weak label instead. Traditional Non-negative Matrix Factorization (NMF) models are not well designed to deal with weakly labeled data. In this paper we propose a novel Masked Non-negative Matrix Factorization (Masked NMF) approach for bird detection using weakly labeled data. During dictionary extraction we introduce a binary mask on the activation matrix. In that way we are able to control which parts of dictionary are used to reconstruct the training data. We compare our method with conventional NMF approaches and current state of the art methods. The proposed method outperforms the NMF baseline and offers a parsimonious model for bird detection on weakly labeled data. Moreover, to our knowledge, the proposed Masked NMF achieved the best result among non-deep learning methods on a test dataset used for the recent Bird Audio Detection Challenge." @default.
- W2758607890 created "2017-10-06" @default.
- W2758607890 creator A5063577296 @default.
- W2758607890 creator A5066967599 @default.
- W2758607890 creator A5072482416 @default.
- W2758607890 date "2017-08-01" @default.
- W2758607890 modified "2023-09-30" @default.
- W2758607890 title "Masked Non-negative Matrix Factorization for Bird Detection Using Weakly Labeled Data" @default.
- W2758607890 cites W1496704041 @default.
- W2758607890 cites W1579308130 @default.
- W2758607890 cites W1902027874 @default.
- W2758607890 cites W2069943693 @default.
- W2758607890 cites W2077159900 @default.
- W2758607890 cites W2090200552 @default.
- W2758607890 cites W2102381657 @default.
- W2758607890 cites W2108494558 @default.
- W2758607890 cites W2114508388 @default.
- W2758607890 cites W2158698691 @default.
- W2758607890 cites W2354870669 @default.
- W2758607890 cites W2518102674 @default.
- W2758607890 cites W2593610980 @default.
- W2758607890 cites W2640630634 @default.
- W2758607890 cites W2911964244 @default.
- W2758607890 doi "https://doi.org/10.23919/eusipco.2017.8081513" @default.
- W2758607890 hasPublicationYear "2017" @default.
- W2758607890 type Work @default.
- W2758607890 sameAs 2758607890 @default.
- W2758607890 citedByCount "6" @default.
- W2758607890 countsByYear W27586078902018 @default.
- W2758607890 countsByYear W27586078902019 @default.
- W2758607890 countsByYear W27586078902020 @default.
- W2758607890 countsByYear W27586078902023 @default.
- W2758607890 crossrefType "proceedings-article" @default.
- W2758607890 hasAuthorship W2758607890A5063577296 @default.
- W2758607890 hasAuthorship W2758607890A5066967599 @default.
- W2758607890 hasAuthorship W2758607890A5072482416 @default.
- W2758607890 hasBestOaLocation W27586078902 @default.
- W2758607890 hasConcept C106487976 @default.
- W2758607890 hasConcept C113954288 @default.
- W2758607890 hasConcept C121332964 @default.
- W2758607890 hasConcept C124101348 @default.
- W2758607890 hasConcept C152671427 @default.
- W2758607890 hasConcept C153180895 @default.
- W2758607890 hasConcept C154945302 @default.
- W2758607890 hasConcept C158693339 @default.
- W2758607890 hasConcept C159985019 @default.
- W2758607890 hasConcept C192562407 @default.
- W2758607890 hasConcept C2776145971 @default.
- W2758607890 hasConcept C28490314 @default.
- W2758607890 hasConcept C33923547 @default.
- W2758607890 hasConcept C38652104 @default.
- W2758607890 hasConcept C41008148 @default.
- W2758607890 hasConcept C42355184 @default.
- W2758607890 hasConcept C45273575 @default.
- W2758607890 hasConcept C48372109 @default.
- W2758607890 hasConcept C62520636 @default.
- W2758607890 hasConcept C94375191 @default.
- W2758607890 hasConceptScore W2758607890C106487976 @default.
- W2758607890 hasConceptScore W2758607890C113954288 @default.
- W2758607890 hasConceptScore W2758607890C121332964 @default.
- W2758607890 hasConceptScore W2758607890C124101348 @default.
- W2758607890 hasConceptScore W2758607890C152671427 @default.
- W2758607890 hasConceptScore W2758607890C153180895 @default.
- W2758607890 hasConceptScore W2758607890C154945302 @default.
- W2758607890 hasConceptScore W2758607890C158693339 @default.
- W2758607890 hasConceptScore W2758607890C159985019 @default.
- W2758607890 hasConceptScore W2758607890C192562407 @default.
- W2758607890 hasConceptScore W2758607890C2776145971 @default.
- W2758607890 hasConceptScore W2758607890C28490314 @default.
- W2758607890 hasConceptScore W2758607890C33923547 @default.
- W2758607890 hasConceptScore W2758607890C38652104 @default.
- W2758607890 hasConceptScore W2758607890C41008148 @default.
- W2758607890 hasConceptScore W2758607890C42355184 @default.
- W2758607890 hasConceptScore W2758607890C45273575 @default.
- W2758607890 hasConceptScore W2758607890C48372109 @default.
- W2758607890 hasConceptScore W2758607890C62520636 @default.
- W2758607890 hasConceptScore W2758607890C94375191 @default.
- W2758607890 hasLocation W27586078901 @default.
- W2758607890 hasLocation W27586078902 @default.
- W2758607890 hasLocation W27586078903 @default.
- W2758607890 hasOpenAccess W2758607890 @default.
- W2758607890 hasPrimaryLocation W27586078901 @default.
- W2758607890 hasRelatedWork W1486448290 @default.
- W2758607890 hasRelatedWork W2058269967 @default.
- W2758607890 hasRelatedWork W2081322759 @default.
- W2758607890 hasRelatedWork W2098101267 @default.
- W2758607890 hasRelatedWork W2123043102 @default.
- W2758607890 hasRelatedWork W2549837900 @default.
- W2758607890 hasRelatedWork W2577807713 @default.
- W2758607890 hasRelatedWork W2758607890 @default.
- W2758607890 hasRelatedWork W2798193689 @default.
- W2758607890 hasRelatedWork W4320025953 @default.
- W2758607890 isParatext "false" @default.
- W2758607890 isRetracted "false" @default.
- W2758607890 magId "2758607890" @default.
- W2758607890 workType "article" @default.