FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2621864722> ?p ?o ?g. }

• W2621864722 endingPage "2831" @default.
• W2621864722 startingPage "2816" @default.
• W2621864722 abstract "This paper presents a novel and efficient deep fusion convolutional neural network (DF-CNN) for multimodal 2D+3D facial expression recognition (FER). DF-CNN comprises a feature extraction subnet, a feature fusion subnet, and a softmax layer. In particular, each textured three-dimensional (3D) face scan is represented as six types of 2D facial attribute maps (i.e., geometry map, three normal maps, curvature map, and texture map), all of which are jointly fed into DF-CNN for feature learning and fusion learning, resulting in a highly concentrated facial representation (32-dimensional). Expression prediction is performed by two ways: 1) learning linear support vector machine classifiers using the 32-dimensional fused deep features, or 2) directly performing softmax prediction using the six-dimensional expression probability vectors. Different from existing 3D FER methods, DF-CNN combines feature learning and fusion learning into a single end-to-end training framework. To demonstrate the effectiveness of DF-CNN, we conducted comprehensive experiments to compare the performance of DFCNN with handcrafted features, pre-trained deep features, finetuned deep features, and state-of-the-art methods on three 3D face datasets (i.e., BU-3DFE Subset I, BU-3DFE Subset II, and Bosphorus Subset). In all cases, DF-CNN consistently achieved the best results. To the best of our knowledge, this is the first work of introducing deep CNN to 3D FER and deep learning-based featurelevel fusion for multimodal 2D+3D FER." @default.
• W2621864722 created "2017-06-15" @default.
• W2621864722 creator A5037419606 @default.
• W2621864722 creator A5075938156 @default.
• W2621864722 creator A5078026673 @default.
• W2621864722 creator A5088383805 @default.
• W2621864722 date "2017-12-01" @default.
• W2621864722 modified "2023-10-14" @default.
• W2621864722 title "Multimodal 2D+3D Facial Expression Recognition With Deep Fusion Convolutional Neural Network" @default.
• W2621864722 cites W1040410175 @default.
• W2621864722 cites W1480583224 @default.
• W2621864722 cites W1557043124 @default.
• W2621864722 cites W171902450 @default.
• W2621864722 cites W1967947242 @default.
• W2621864722 cites W1968015059 @default.
• W2621864722 cites W1974210421 @default.
• W2621864722 cites W1978435065 @default.
• W2621864722 cites W1981918162 @default.
• W2621864722 cites W1997145183 @default.
• W2621864722 cites W2006406015 @default.
• W2621864722 cites W2006943008 @default.
• W2621864722 cites W2006952256 @default.
• W2621864722 cites W2011556862 @default.
• W2621864722 cites W2013029619 @default.
• W2621864722 cites W2018776244 @default.
• W2621864722 cites W2021438259 @default.
• W2621864722 cites W2030129920 @default.
• W2621864722 cites W2034069713 @default.
• W2621864722 cites W2051526232 @default.
• W2621864722 cites W2051688810 @default.
• W2621864722 cites W2062118960 @default.
• W2621864722 cites W2065379720 @default.
• W2621864722 cites W2066941820 @default.
• W2621864722 cites W2068610869 @default.
• W2621864722 cites W2069190036 @default.
• W2621864722 cites W2072730064 @default.
• W2621864722 cites W2082645628 @default.
• W2621864722 cites W2083021723 @default.
• W2621864722 cites W2086516372 @default.
• W2621864722 cites W2095399814 @default.
• W2621864722 cites W2102713935 @default.
• W2621864722 cites W2104539097 @default.
• W2621864722 cites W2106947945 @default.
• W2621864722 cites W2109774206 @default.
• W2621864722 cites W2116875963 @default.
• W2621864722 cites W2124901121 @default.
• W2621864722 cites W2134592850 @default.
• W2621864722 cites W2139916508 @default.
• W2621864722 cites W2143829622 @default.
• W2621864722 cites W2149563102 @default.
• W2621864722 cites W2150293569 @default.
• W2621864722 cites W2151430047 @default.
• W2621864722 cites W2159017231 @default.
• W2621864722 cites W2163864141 @default.
• W2621864722 cites W2164623278 @default.
• W2621864722 cites W2174772062 @default.
• W2621864722 cites W2195207531 @default.
• W2621864722 cites W2246249023 @default.
• W2621864722 cites W2294427751 @default.
• W2621864722 cites W2301789900 @default.
• W2621864722 cites W2326887180 @default.
• W2621864722 cites W2339620988 @default.
• W2621864722 cites W2345305417 @default.
• W2621864722 cites W300533172 @default.
• W2621864722 doi "https://doi.org/10.1109/tmm.2017.2713408" @default.
• W2621864722 hasPublicationYear "2017" @default.
• W2621864722 type Work @default.
• W2621864722 sameAs 2621864722 @default.
• W2621864722 citedByCount "164" @default.
• W2621864722 countsByYear W26218647222018 @default.
• W2621864722 countsByYear W26218647222019 @default.
• W2621864722 countsByYear W26218647222020 @default.
• W2621864722 countsByYear W26218647222021 @default.
• W2621864722 countsByYear W26218647222022 @default.
• W2621864722 countsByYear W26218647222023 @default.
• W2621864722 crossrefType "journal-article" @default.
• W2621864722 hasAuthorship W2621864722A5037419606 @default.
• W2621864722 hasAuthorship W2621864722A5075938156 @default.
• W2621864722 hasAuthorship W2621864722A5078026673 @default.
• W2621864722 hasAuthorship W2621864722A5088383805 @default.
• W2621864722 hasConcept C108583219 @default.
• W2621864722 hasConcept C138885662 @default.
• W2621864722 hasConcept C153180895 @default.
• W2621864722 hasConcept C154945302 @default.
• W2621864722 hasConcept C188441871 @default.
• W2621864722 hasConcept C21099817 @default.
• W2621864722 hasConcept C2776401178 @default.
• W2621864722 hasConcept C31258907 @default.
• W2621864722 hasConcept C41008148 @default.
• W2621864722 hasConcept C41895202 @default.
• W2621864722 hasConcept C52622490 @default.
• W2621864722 hasConcept C59404180 @default.
• W2621864722 hasConcept C81363708 @default.
• W2621864722 hasConceptScore W2621864722C108583219 @default.
• W2621864722 hasConceptScore W2621864722C138885662 @default.
• W2621864722 hasConceptScore W2621864722C153180895 @default.
• W2621864722 hasConceptScore W2621864722C154945302 @default.
• W2621864722 hasConceptScore W2621864722C188441871 @default.

• next