Matches in SemOpenAlex for { <https://semopenalex.org/work/W2884142018> ?p ?o ?g. }
- W2884142018 abstract "In time series classification, signals are typically mapped into some intermediate representation which is used to construct models. We introduce the joint time-frequency scattering transform, a locally time-shift invariant representation which characterizes the multiscale energy distribution of a signal in time and frequency. It is computed through wavelet convolutions and modulus non-linearities and may therefore be implemented as a deep convolutional neural network whose filters are not learned but calculated from wavelets. We consider the progression from mel-spectrograms to time scattering and joint time-frequency scattering transforms, illustrating the relationship between increased discriminability and refinements of convolutional network architectures. The suitability of the joint time-frequency scattering transform for characterizing time series is demonstrated through applications to chirp signals and audio synthesis experiments. The proposed transform also obtains state-of-the-art results on several audio classification tasks, outperforming time scattering transforms and achieving accuracies comparable to those of fully learned networks." @default.
- W2884142018 created "2018-08-03" @default.
- W2884142018 creator A5027789239 @default.
- W2884142018 creator A5043290570 @default.
- W2884142018 creator A5065086376 @default.
- W2884142018 date "2018-07-24" @default.
- W2884142018 modified "2023-09-27" @default.
- W2884142018 title "Classification with Joint Time-Frequency Scattering." @default.
- W2884142018 cites W104184427 @default.
- W2884142018 cites W1641465689 @default.
- W2884142018 cites W1897037354 @default.
- W2884142018 cites W1990934990 @default.
- W2884142018 cites W1990938546 @default.
- W2884142018 cites W1994396704 @default.
- W2884142018 cites W2015861736 @default.
- W2884142018 cites W2023262923 @default.
- W2884142018 cites W2038484192 @default.
- W2884142018 cites W2046331056 @default.
- W2884142018 cites W2054139811 @default.
- W2884142018 cites W2059511347 @default.
- W2884142018 cites W2062024414 @default.
- W2884142018 cites W2062663442 @default.
- W2884142018 cites W2072072671 @default.
- W2884142018 cites W2076063813 @default.
- W2884142018 cites W2077804127 @default.
- W2884142018 cites W2093231248 @default.
- W2884142018 cites W2107157326 @default.
- W2884142018 cites W2112796928 @default.
- W2884142018 cites W2115755118 @default.
- W2884142018 cites W2119821739 @default.
- W2884142018 cites W2130426352 @default.
- W2884142018 cites W2143612262 @default.
- W2884142018 cites W2148154194 @default.
- W2884142018 cites W2149241068 @default.
- W2884142018 cites W2153635508 @default.
- W2884142018 cites W2154833897 @default.
- W2884142018 cites W2164877274 @default.
- W2884142018 cites W2167383966 @default.
- W2884142018 cites W2293255527 @default.
- W2884142018 cites W2296724634 @default.
- W2884142018 cites W2296751288 @default.
- W2884142018 cites W2328848613 @default.
- W2884142018 cites W2398826216 @default.
- W2884142018 cites W2400549570 @default.
- W2884142018 cites W2403175639 @default.
- W2884142018 cites W2408093180 @default.
- W2884142018 cites W2544224704 @default.
- W2884142018 cites W2798506522 @default.
- W2884142018 cites W2804005492 @default.
- W2884142018 cites W2888740332 @default.
- W2884142018 cites W2891171253 @default.
- W2884142018 cites W2893538338 @default.
- W2884142018 cites W2914312680 @default.
- W2884142018 cites W2950265320 @default.
- W2884142018 cites W2952558884 @default.
- W2884142018 cites W595851582 @default.
- W2884142018 cites W9692546 @default.
- W2884142018 hasPublicationYear "2018" @default.
- W2884142018 type Work @default.
- W2884142018 sameAs 2884142018 @default.
- W2884142018 citedByCount "5" @default.
- W2884142018 countsByYear W28841420182018 @default.
- W2884142018 countsByYear W28841420182019 @default.
- W2884142018 crossrefType "posted-content" @default.
- W2884142018 hasAuthorship W2884142018A5027789239 @default.
- W2884142018 hasAuthorship W2884142018A5043290570 @default.
- W2884142018 hasAuthorship W2884142018A5065086376 @default.
- W2884142018 hasConcept C102519508 @default.
- W2884142018 hasConcept C106131492 @default.
- W2884142018 hasConcept C11413529 @default.
- W2884142018 hasConcept C120665830 @default.
- W2884142018 hasConcept C121332964 @default.
- W2884142018 hasConcept C124062153 @default.
- W2884142018 hasConcept C127413603 @default.
- W2884142018 hasConcept C134306372 @default.
- W2884142018 hasConcept C142433447 @default.
- W2884142018 hasConcept C153180895 @default.
- W2884142018 hasConcept C154945302 @default.
- W2884142018 hasConcept C170154142 @default.
- W2884142018 hasConcept C18555067 @default.
- W2884142018 hasConcept C191486275 @default.
- W2884142018 hasConcept C196216189 @default.
- W2884142018 hasConcept C31972630 @default.
- W2884142018 hasConcept C33923547 @default.
- W2884142018 hasConcept C41008148 @default.
- W2884142018 hasConcept C45273575 @default.
- W2884142018 hasConcept C46286280 @default.
- W2884142018 hasConcept C47432892 @default.
- W2884142018 hasConcept C95722684 @default.
- W2884142018 hasConceptScore W2884142018C102519508 @default.
- W2884142018 hasConceptScore W2884142018C106131492 @default.
- W2884142018 hasConceptScore W2884142018C11413529 @default.
- W2884142018 hasConceptScore W2884142018C120665830 @default.
- W2884142018 hasConceptScore W2884142018C121332964 @default.
- W2884142018 hasConceptScore W2884142018C124062153 @default.
- W2884142018 hasConceptScore W2884142018C127413603 @default.
- W2884142018 hasConceptScore W2884142018C134306372 @default.
- W2884142018 hasConceptScore W2884142018C142433447 @default.
- W2884142018 hasConceptScore W2884142018C153180895 @default.
- W2884142018 hasConceptScore W2884142018C154945302 @default.