Matches in SemOpenAlex for { <https://semopenalex.org/work/W3068731427> ?p ?o ?g. }
- W3068731427 abstract "In this paper, we present a sparsity-aware deep network for automatic 4D facial expression recognition (FER). Given 4D data, we first propose a novel augmentation method to combat the data limitation problem for deep learning. This is achieved by projecting the input data into RGB and depth map images and then iteratively performing randomized channel concatenation. Encoded in the given 3D landmarks, we also introduce an effective way to capture the facial muscle movements from three orthogonal plans (TOP), the TOP-landmarks over multi-views. Importantly, we then present a sparsity-aware deep network to compute the sparse representations of convolutional features over multi-views. This is not only effective for a higher recognition accuracy but is also computationally convenient. For training, the TOP-landmarks and sparse representations are used to train a long short-term memory (LSTM) network. The refined predictions are achieved when the learned features collaborate over multi-views. Extensive experimental results achieved on the BU-4DFE dataset show the significance of our method over the state-of-the-art methods by reaching a promising accuracy of 99.69% for 4D FER." @default.
- W3068731427 created "2020-08-24" @default.
- W3068731427 creator A5034624002 @default.
- W3068731427 creator A5042947456 @default.
- W3068731427 creator A5080110930 @default.
- W3068731427 creator A5082301986 @default.
- W3068731427 date "2020-02-08" @default.
- W3068731427 modified "2023-10-18" @default.
- W3068731427 title "Towards Reading Beyond Faces for Sparsity-Aware 4D Affect Recognition" @default.
- W3068731427 cites W1040410175 @default.
- W3068731427 cites W1603155784 @default.
- W3068731427 cites W1935978687 @default.
- W3068731427 cites W1973122439 @default.
- W3068731427 cites W1988744266 @default.
- W3068731427 cites W1992146740 @default.
- W3068731427 cites W1997145183 @default.
- W3068731427 cites W2003238582 @default.
- W3068731427 cites W2011556862 @default.
- W3068731427 cites W2018727909 @default.
- W3068731427 cites W2018776244 @default.
- W3068731427 cites W2033773055 @default.
- W3068731427 cites W2060488580 @default.
- W3068731427 cites W2068610869 @default.
- W3068731427 cites W2069190036 @default.
- W3068731427 cites W2072072671 @default.
- W3068731427 cites W2076617402 @default.
- W3068731427 cites W2084283003 @default.
- W3068731427 cites W2097117768 @default.
- W3068731427 cites W2102539767 @default.
- W3068731427 cites W2104539097 @default.
- W3068731427 cites W2117539524 @default.
- W3068731427 cites W2123937777 @default.
- W3068731427 cites W2139916508 @default.
- W3068731427 cites W2156503193 @default.
- W3068731427 cites W2163605009 @default.
- W3068731427 cites W2169798735 @default.
- W3068731427 cites W2170093232 @default.
- W3068731427 cites W2183341477 @default.
- W3068731427 cites W2194775991 @default.
- W3068731427 cites W2339620988 @default.
- W3068731427 cites W2487852963 @default.
- W3068731427 cites W2621864722 @default.
- W3068731427 cites W2750821397 @default.
- W3068731427 cites W2752758619 @default.
- W3068731427 cites W2794377003 @default.
- W3068731427 cites W2799041689 @default.
- W3068731427 cites W2805781993 @default.
- W3068731427 cites W2806234218 @default.
- W3068731427 cites W2891410536 @default.
- W3068731427 cites W2942372587 @default.
- W3068731427 cites W2963322354 @default.
- W3068731427 cites W3023712337 @default.
- W3068731427 cites W3034588700 @default.
- W3068731427 doi "https://doi.org/10.48550/arxiv.2002.03157" @default.
- W3068731427 hasPublicationYear "2020" @default.
- W3068731427 type Work @default.
- W3068731427 sameAs 3068731427 @default.
- W3068731427 citedByCount "0" @default.
- W3068731427 crossrefType "posted-content" @default.
- W3068731427 hasAuthorship W3068731427A5034624002 @default.
- W3068731427 hasAuthorship W3068731427A5042947456 @default.
- W3068731427 hasAuthorship W3068731427A5080110930 @default.
- W3068731427 hasAuthorship W3068731427A5082301986 @default.
- W3068731427 hasBestOaLocation W30687314271 @default.
- W3068731427 hasConcept C108583219 @default.
- W3068731427 hasConcept C114614502 @default.
- W3068731427 hasConcept C153180895 @default.
- W3068731427 hasConcept C154945302 @default.
- W3068731427 hasConcept C28490314 @default.
- W3068731427 hasConcept C33923547 @default.
- W3068731427 hasConcept C41008148 @default.
- W3068731427 hasConcept C81363708 @default.
- W3068731427 hasConcept C82990744 @default.
- W3068731427 hasConcept C87619178 @default.
- W3068731427 hasConceptScore W3068731427C108583219 @default.
- W3068731427 hasConceptScore W3068731427C114614502 @default.
- W3068731427 hasConceptScore W3068731427C153180895 @default.
- W3068731427 hasConceptScore W3068731427C154945302 @default.
- W3068731427 hasConceptScore W3068731427C28490314 @default.
- W3068731427 hasConceptScore W3068731427C33923547 @default.
- W3068731427 hasConceptScore W3068731427C41008148 @default.
- W3068731427 hasConceptScore W3068731427C81363708 @default.
- W3068731427 hasConceptScore W3068731427C82990744 @default.
- W3068731427 hasConceptScore W3068731427C87619178 @default.
- W3068731427 hasLocation W30687314271 @default.
- W3068731427 hasOpenAccess W3068731427 @default.
- W3068731427 hasPrimaryLocation W30687314271 @default.
- W3068731427 hasRelatedWork W2557924869 @default.
- W3068731427 hasRelatedWork W2732542196 @default.
- W3068731427 hasRelatedWork W2738221750 @default.
- W3068731427 hasRelatedWork W2774550181 @default.
- W3068731427 hasRelatedWork W2800691917 @default.
- W3068731427 hasRelatedWork W2940661641 @default.
- W3068731427 hasRelatedWork W3126336475 @default.
- W3068731427 hasRelatedWork W3213960077 @default.
- W3068731427 hasRelatedWork W4214561993 @default.
- W3068731427 hasRelatedWork W564581980 @default.
- W3068731427 isParatext "false" @default.
- W3068731427 isRetracted "false" @default.
- W3068731427 magId "3068731427" @default.