FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3012017992> ?p ?o ?g. }

• W3012017992 abstract "Non-verbal forms of communication are universal, being free of any language barrier and widely used in all art forms. For example, in Bharatanatyam, an ancient Indian dance form, artists use different hand gestures, body postures and facial expressions to convey the story line. As identification and classification of these complex and multivariant visual images are difficult, it is now being addressed with the help of advanced computer vision techniques and deep neural networks. This work deals with studies in automation of identification, classification and labelling of selected Bharatnatyam gestures, as part of our efforts to preserve this rich cultural heritage for future generations. The classification of the mudras against their true labels was carried out using different singular pre-trained / non-pre-trained as well as stacked ensemble convolutional neural architectures (CNNs). In all, twenty-seven classes of asamyukta hasta (single hand gestures) data were collected from Google, YouTube and few real time performances by artists. Since the background in many frames are highly diverse, the acquired data is real and dynamic, compared to images from closed laboratory settings. The cleansing of mislabeled data from the dataset was done through label transferring based on distance-based similarity metric using convolutional siamese neural network. The classification of mudras was done using different CNN architecture: i) singular models, ii) ensemble models, and iii) few specialized models. This study achieved an accuracy of >95%, both in single and double transfer learning models, as well as their stacked ensemble model. The results emphasize the crucial role of domain similarity of the pre-training / training datasets for improved classification accuracy and, also indicate that doubly pre-trained CNN model yield the highest accuracy." @default.
• W3012017992 created "2020-03-23" @default.
• W3012017992 creator A5020757309 @default.
• W3012017992 creator A5036015078 @default.
• W3012017992 creator A5049549744 @default.
• W3012017992 creator A5079063339 @default.
• W3012017992 date "2020-01-01" @default.
• W3012017992 modified "2023-09-23" @default.
• W3012017992 title "Unravelling of Convolutional Neural Networks through Bharatanatyam Mudra Classification with Limited Data" @default.
• W3012017992 cites W16452475 @default.
• W3012017992 cites W1998082750 @default.
• W3012017992 cites W2001644664 @default.
• W3012017992 cites W2024922353 @default.
• W3012017992 cites W2043011727 @default.
• W3012017992 cites W2086235688 @default.
• W3012017992 cites W2100683382 @default.
• W3012017992 cites W2108598243 @default.
• W3012017992 cites W2127589108 @default.
• W3012017992 cites W2162320392 @default.
• W3012017992 cites W2194775991 @default.
• W3012017992 cites W2525713776 @default.
• W3012017992 cites W2534295310 @default.
• W3012017992 cites W2545384545 @default.
• W3012017992 cites W2806921399 @default.
• W3012017992 cites W2894391280 @default.
• W3012017992 cites W4246305470 @default.
• W3012017992 doi "https://doi.org/10.1109/ccwc47524.2020.9031185" @default.
• W3012017992 hasPublicationYear "2020" @default.
• W3012017992 type Work @default.
• W3012017992 sameAs 3012017992 @default.
• W3012017992 citedByCount "6" @default.
• W3012017992 countsByYear W30120179922021 @default.
• W3012017992 countsByYear W30120179922022 @default.
• W3012017992 countsByYear W30120179922023 @default.
• W3012017992 crossrefType "proceedings-article" @default.
• W3012017992 hasAuthorship W3012017992A5020757309 @default.
• W3012017992 hasAuthorship W3012017992A5036015078 @default.
• W3012017992 hasAuthorship W3012017992A5049549744 @default.
• W3012017992 hasAuthorship W3012017992A5079063339 @default.
• W3012017992 hasConcept C119857082 @default.
• W3012017992 hasConcept C154945302 @default.
• W3012017992 hasConcept C204321447 @default.
• W3012017992 hasConcept C41008148 @default.
• W3012017992 hasConcept C50644808 @default.
• W3012017992 hasConcept C81363708 @default.
• W3012017992 hasConceptScore W3012017992C119857082 @default.
• W3012017992 hasConceptScore W3012017992C154945302 @default.
• W3012017992 hasConceptScore W3012017992C204321447 @default.
• W3012017992 hasConceptScore W3012017992C41008148 @default.
• W3012017992 hasConceptScore W3012017992C50644808 @default.
• W3012017992 hasConceptScore W3012017992C81363708 @default.
• W3012017992 hasLocation W30120179921 @default.
• W3012017992 hasOpenAccess W3012017992 @default.
• W3012017992 hasPrimaryLocation W30120179921 @default.
• W3012017992 hasRelatedWork W2337926734 @default.
• W3012017992 hasRelatedWork W2963958939 @default.
• W3012017992 hasRelatedWork W3021430260 @default.
• W3012017992 hasRelatedWork W3027997911 @default.
• W3012017992 hasRelatedWork W3107474891 @default.
• W3012017992 hasRelatedWork W4287776258 @default.
• W3012017992 hasRelatedWork W4312501200 @default.
• W3012017992 hasRelatedWork W4313050734 @default.
• W3012017992 hasRelatedWork W4320802194 @default.
• W3012017992 hasRelatedWork W1629725936 @default.
• W3012017992 isParatext "false" @default.
• W3012017992 isRetracted "false" @default.
• W3012017992 magId "3012017992" @default.
• W3012017992 workType "article" @default.