Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092363664> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3092363664 endingPage "186" @default.
- W3092363664 startingPage "172" @default.
- W3092363664 abstract "In this paper, we propose novel stochastic modeling of various components of a continuous sign language recognition (CSLR) system that is based on the transformer encoder and connectionist temporal classification (CTC). Most importantly, We model each sign gloss with multiple states, and the number of states is a categorical random variable that follows a learned probability distribution, providing stochastic fine-grained labels for training the CTC decoder. We further propose a stochastic frame dropping mechanism and a gradient stopping method to deal with the severe overfitting problem in training the transformer model with CTC loss. These two methods also help reduce the training computation, both in terms of time and space, significantly. We evaluated our model on popular CSLR datasets, and show its effectiveness compared to the state-of-the-art methods." @default.
- W3092363664 created "2020-10-15" @default.
- W3092363664 creator A5031380432 @default.
- W3092363664 creator A5059141717 @default.
- W3092363664 date "2020-01-01" @default.
- W3092363664 modified "2023-10-01" @default.
- W3092363664 title "Stochastic Fine-Grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition" @default.
- W3092363664 cites W2097117768 @default.
- W3092363664 cites W2117539524 @default.
- W3092363664 cites W2188882108 @default.
- W3092363664 cites W2194775991 @default.
- W3092363664 cites W2587277634 @default.
- W3092363664 cites W2746301562 @default.
- W3092363664 cites W2755802490 @default.
- W3092363664 cites W2759302818 @default.
- W3092363664 cites W2799020610 @default.
- W3092363664 cites W2897247225 @default.
- W3092363664 cites W2941870244 @default.
- W3092363664 cites W2948139159 @default.
- W3092363664 cites W2963925437 @default.
- W3092363664 cites W2964253156 @default.
- W3092363664 cites W2966344125 @default.
- W3092363664 cites W2971108547 @default.
- W3092363664 cites W2972451902 @default.
- W3092363664 doi "https://doi.org/10.1007/978-3-030-58517-4_11" @default.
- W3092363664 hasPublicationYear "2020" @default.
- W3092363664 type Work @default.
- W3092363664 sameAs 3092363664 @default.
- W3092363664 citedByCount "25" @default.
- W3092363664 countsByYear W30923636642021 @default.
- W3092363664 countsByYear W30923636642022 @default.
- W3092363664 countsByYear W30923636642023 @default.
- W3092363664 crossrefType "book-chapter" @default.
- W3092363664 hasAuthorship W3092363664A5031380432 @default.
- W3092363664 hasAuthorship W3092363664A5059141717 @default.
- W3092363664 hasConcept C108583219 @default.
- W3092363664 hasConcept C11413529 @default.
- W3092363664 hasConcept C121332964 @default.
- W3092363664 hasConcept C137293760 @default.
- W3092363664 hasConcept C138885662 @default.
- W3092363664 hasConcept C153180895 @default.
- W3092363664 hasConcept C154945302 @default.
- W3092363664 hasConcept C165801399 @default.
- W3092363664 hasConcept C188441871 @default.
- W3092363664 hasConcept C28490314 @default.
- W3092363664 hasConcept C41008148 @default.
- W3092363664 hasConcept C41895202 @default.
- W3092363664 hasConcept C522192633 @default.
- W3092363664 hasConcept C62520636 @default.
- W3092363664 hasConcept C66322947 @default.
- W3092363664 hasConceptScore W3092363664C108583219 @default.
- W3092363664 hasConceptScore W3092363664C11413529 @default.
- W3092363664 hasConceptScore W3092363664C121332964 @default.
- W3092363664 hasConceptScore W3092363664C137293760 @default.
- W3092363664 hasConceptScore W3092363664C138885662 @default.
- W3092363664 hasConceptScore W3092363664C153180895 @default.
- W3092363664 hasConceptScore W3092363664C154945302 @default.
- W3092363664 hasConceptScore W3092363664C165801399 @default.
- W3092363664 hasConceptScore W3092363664C188441871 @default.
- W3092363664 hasConceptScore W3092363664C28490314 @default.
- W3092363664 hasConceptScore W3092363664C41008148 @default.
- W3092363664 hasConceptScore W3092363664C41895202 @default.
- W3092363664 hasConceptScore W3092363664C522192633 @default.
- W3092363664 hasConceptScore W3092363664C62520636 @default.
- W3092363664 hasConceptScore W3092363664C66322947 @default.
- W3092363664 hasLocation W30923636641 @default.
- W3092363664 hasOpenAccess W3092363664 @default.
- W3092363664 hasPrimaryLocation W30923636641 @default.
- W3092363664 hasRelatedWork W2743258233 @default.
- W3092363664 hasRelatedWork W2758063741 @default.
- W3092363664 hasRelatedWork W2807311372 @default.
- W3092363664 hasRelatedWork W2976243291 @default.
- W3092363664 hasRelatedWork W2977314777 @default.
- W3092363664 hasRelatedWork W2997969508 @default.
- W3092363664 hasRelatedWork W3208883981 @default.
- W3092363664 hasRelatedWork W3214058074 @default.
- W3092363664 hasRelatedWork W4307834408 @default.
- W3092363664 hasRelatedWork W4320925816 @default.
- W3092363664 isParatext "false" @default.
- W3092363664 isRetracted "false" @default.
- W3092363664 magId "3092363664" @default.
- W3092363664 workType "book-chapter" @default.