FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197409377> ?p ?o ?g. }

• W3197409377 endingPage "18145" @default.
• W3197409377 startingPage "18131" @default.
• W3197409377 abstract "Emotion recognition (ER) from facial images is one of the landmark tasks in affective computing with major developments in the last decade. Initial efforts on ER relied on handcrafted features that were used to characterize facial images and then feed to standard predictive models. Recent methodologies comprise end-to-end trainable deep learning methods that simultaneously learn both, features and predictive model. Perhaps the most successful models are based on convolutional neural networks (CNNs). While these models have excelled at this task, they still fail at capturing local patterns that could emerge in the learning process. We hypothesize these patterns could be captured by variants based on locally weighted learning. Specifically, in this paper we propose a CNN based architecture enhanced with multiple branches formed by radial basis function (RBF) units that aims at exploiting local information at the final stage of the learning process. Intuitively, these RBF units capture local patterns shared by similar instances using an intermediate representation, then the outputs of the RBFs are feed to a softmax layer that exploits this information to improve the predictive performance of the model. This feature could be particularly advantageous in ER as cultural / ethnicity differences may be identified by the local units. We evaluate the proposed method in several ER datasets and show the proposed methodology achieves state-of-the-art in some of them, even when we adopt a pre-trained VGG-Face model as backbone. We show it is the incorporation of local information what makes the proposed model competitive." @default.
• W3197409377 created "2021-09-13" @default.
• W3197409377 creator A5003897232 @default.
• W3197409377 creator A5076464455 @default.
• W3197409377 date "2021-08-27" @default.
• W3197409377 modified "2023-09-26" @default.
• W3197409377 title "Multi-branch deep radial basis function networks for facial emotion recognition" @default.
• W3197409377 cites W1166996211 @default.
• W3197409377 cites W1996958556 @default.
• W3197409377 cites W2024605627 @default.
• W3197409377 cites W2041616772 @default.
• W3197409377 cites W2068610869 @default.
• W3197409377 cites W2097117768 @default.
• W3197409377 cites W2103943262 @default.
• W3197409377 cites W2106115875 @default.
• W3197409377 cites W2139916508 @default.
• W3197409377 cites W2145310492 @default.
• W3197409377 cites W2151941540 @default.
• W3197409377 cites W2186408627 @default.
• W3197409377 cites W2194775991 @default.
• W3197409377 cites W2244142460 @default.
• W3197409377 cites W2325939864 @default.
• W3197409377 cites W2490049321 @default.
• W3197409377 cites W2546815878 @default.
• W3197409377 cites W2602990925 @default.
• W3197409377 cites W2730601341 @default.
• W3197409377 cites W2738672149 @default.
• W3197409377 cites W2762582125 @default.
• W3197409377 cites W2798506093 @default.
• W3197409377 cites W2802379451 @default.
• W3197409377 cites W2805755230 @default.
• W3197409377 cites W2889978276 @default.
• W3197409377 cites W2891187402 @default.
• W3197409377 cites W2893657794 @default.
• W3197409377 cites W2896277673 @default.
• W3197409377 cites W2899092732 @default.
• W3197409377 cites W2995396423 @default.
• W3197409377 cites W2996033780 @default.
• W3197409377 cites W3001196836 @default.
• W3197409377 cites W3003720578 @default.
• W3197409377 cites W3005529595 @default.
• W3197409377 cites W3020105295 @default.
• W3197409377 cites W3035336958 @default.
• W3197409377 cites W3035565904 @default.
• W3197409377 cites W3040550475 @default.
• W3197409377 cites W3044295043 @default.
• W3197409377 cites W3056251842 @default.
• W3197409377 cites W3088046705 @default.
• W3197409377 cites W3099206234 @default.
• W3197409377 cites W3101446709 @default.
• W3197409377 cites W3102749295 @default.
• W3197409377 cites W3104210646 @default.
• W3197409377 cites W4313016726 @default.
• W3197409377 doi "https://doi.org/10.1007/s00521-021-06420-w" @default.
• W3197409377 hasPublicationYear "2021" @default.
• W3197409377 type Work @default.
• W3197409377 sameAs 3197409377 @default.
• W3197409377 citedByCount "6" @default.
• W3197409377 countsByYear W31974093772022 @default.
• W3197409377 countsByYear W31974093772023 @default.
• W3197409377 crossrefType "journal-article" @default.
• W3197409377 hasAuthorship W3197409377A5003897232 @default.
• W3197409377 hasAuthorship W3197409377A5076464455 @default.
• W3197409377 hasBestOaLocation W31974093772 @default.
• W3197409377 hasConcept C108583219 @default.
• W3197409377 hasConcept C111919701 @default.
• W3197409377 hasConcept C119857082 @default.
• W3197409377 hasConcept C138885662 @default.
• W3197409377 hasConcept C14036430 @default.
• W3197409377 hasConcept C144024400 @default.
• W3197409377 hasConcept C153180895 @default.
• W3197409377 hasConcept C154945302 @default.
• W3197409377 hasConcept C165696696 @default.
• W3197409377 hasConcept C17744445 @default.
• W3197409377 hasConcept C188441871 @default.
• W3197409377 hasConcept C199539241 @default.
• W3197409377 hasConcept C2776359362 @default.
• W3197409377 hasConcept C2776401178 @default.
• W3197409377 hasConcept C2779304628 @default.
• W3197409377 hasConcept C36289849 @default.
• W3197409377 hasConcept C38652104 @default.
• W3197409377 hasConcept C41008148 @default.
• W3197409377 hasConcept C41895202 @default.
• W3197409377 hasConcept C50644808 @default.
• W3197409377 hasConcept C78458016 @default.
• W3197409377 hasConcept C81363708 @default.
• W3197409377 hasConcept C86803240 @default.
• W3197409377 hasConcept C94625758 @default.
• W3197409377 hasConcept C98045186 @default.
• W3197409377 hasConcept C98856871 @default.
• W3197409377 hasConceptScore W3197409377C108583219 @default.
• W3197409377 hasConceptScore W3197409377C111919701 @default.
• W3197409377 hasConceptScore W3197409377C119857082 @default.
• W3197409377 hasConceptScore W3197409377C138885662 @default.
• W3197409377 hasConceptScore W3197409377C14036430 @default.
• W3197409377 hasConceptScore W3197409377C144024400 @default.
• W3197409377 hasConceptScore W3197409377C153180895 @default.
• W3197409377 hasConceptScore W3197409377C154945302 @default.

• next