Matches in SemOpenAlex for { <https://semopenalex.org/work/W2794091644> ?p ?o ?g. }
- W2794091644 abstract "Meaningful facial parts can convey key cues for both facial action unit detection and expression prediction. Textured 3D face scan can provide both detailed 3D geometric shape and 2D texture appearance cues of the face which are beneficial for Facial Expression Recognition (FER). However, accurate facial parts extraction as well as their fusion are challenging tasks. In this paper, a novel system for 3D FER is designed based on accurate facial parts extraction and deep feature fusion of facial parts. In particular, each textured 3D face scan is firstly represented as a 2D texture map and a depth map with one-to-one dense correspondence. Then, the facial parts of both texture map and depth map are extracted using a novel 4-stage process consists of facial landmark localization, facial rotation correction, facial resizing, facial parts bounding box extraction and post-processing procedures. Finally, deep fusion Convolutional Neural Networks (CNNs) features of all facial parts are learned from both texture maps and depth maps, respectively and nonlinear SVMs are used for expression prediction. Experiments are conducted on the BU-3DFE database, demonstrating the effectiveness of combing different facial parts, texture and depth cues and reporting the state-of-the-art results in comparison with all existing methods under the same setting." @default.
- W2794091644 created "2018-03-29" @default.
- W2794091644 creator A5020940044 @default.
- W2794091644 creator A5023275144 @default.
- W2794091644 creator A5046176052 @default.
- W2794091644 creator A5078026673 @default.
- W2794091644 creator A5088383805 @default.
- W2794091644 date "2018-03-04" @default.
- W2794091644 modified "2023-09-23" @default.
- W2794091644 title "Accurate Facial Parts Localization and Deep Learning for 3D Facial Expression Recognition" @default.
- W2794091644 cites W104184427 @default.
- W2794091644 cites W1603155784 @default.
- W2794091644 cites W1677182931 @default.
- W2794091644 cites W1874719077 @default.
- W2794091644 cites W1963882359 @default.
- W2794091644 cites W1974210421 @default.
- W2794091644 cites W1978435065 @default.
- W2794091644 cites W1994002998 @default.
- W2794091644 cites W1998294030 @default.
- W2794091644 cites W2006943008 @default.
- W2794091644 cites W2021438259 @default.
- W2794091644 cites W2051688810 @default.
- W2794091644 cites W2065379720 @default.
- W2794091644 cites W2101866605 @default.
- W2794091644 cites W2121684305 @default.
- W2794091644 cites W2136063698 @default.
- W2794091644 cites W2136922672 @default.
- W2794091644 cites W2157285372 @default.
- W2794091644 cites W2161969291 @default.
- W2794091644 cites W2163352848 @default.
- W2794091644 cites W2339620988 @default.
- W2794091644 cites W2589142773 @default.
- W2794091644 cites W2621864722 @default.
- W2794091644 cites W2676551185 @default.
- W2794091644 cites W2971794874 @default.
- W2794091644 doi "https://doi.org/10.48550/arxiv.1803.05846" @default.
- W2794091644 hasPublicationYear "2018" @default.
- W2794091644 type Work @default.
- W2794091644 sameAs 2794091644 @default.
- W2794091644 citedByCount "0" @default.
- W2794091644 crossrefType "posted-content" @default.
- W2794091644 hasAuthorship W2794091644A5020940044 @default.
- W2794091644 hasAuthorship W2794091644A5023275144 @default.
- W2794091644 hasAuthorship W2794091644A5046176052 @default.
- W2794091644 hasAuthorship W2794091644A5078026673 @default.
- W2794091644 hasAuthorship W2794091644A5088383805 @default.
- W2794091644 hasBestOaLocation W27940916441 @default.
- W2794091644 hasConcept C115961682 @default.
- W2794091644 hasConcept C138885662 @default.
- W2794091644 hasConcept C144024400 @default.
- W2794091644 hasConcept C153180895 @default.
- W2794091644 hasConcept C154945302 @default.
- W2794091644 hasConcept C195704467 @default.
- W2794091644 hasConcept C2776401178 @default.
- W2794091644 hasConcept C2779304628 @default.
- W2794091644 hasConcept C2781195486 @default.
- W2794091644 hasConcept C31510193 @default.
- W2794091644 hasConcept C31972630 @default.
- W2794091644 hasConcept C36289849 @default.
- W2794091644 hasConcept C41008148 @default.
- W2794091644 hasConcept C41895202 @default.
- W2794091644 hasConcept C4641261 @default.
- W2794091644 hasConcept C52622490 @default.
- W2794091644 hasConcept C54654163 @default.
- W2794091644 hasConcept C81363708 @default.
- W2794091644 hasConceptScore W2794091644C115961682 @default.
- W2794091644 hasConceptScore W2794091644C138885662 @default.
- W2794091644 hasConceptScore W2794091644C144024400 @default.
- W2794091644 hasConceptScore W2794091644C153180895 @default.
- W2794091644 hasConceptScore W2794091644C154945302 @default.
- W2794091644 hasConceptScore W2794091644C195704467 @default.
- W2794091644 hasConceptScore W2794091644C2776401178 @default.
- W2794091644 hasConceptScore W2794091644C2779304628 @default.
- W2794091644 hasConceptScore W2794091644C2781195486 @default.
- W2794091644 hasConceptScore W2794091644C31510193 @default.
- W2794091644 hasConceptScore W2794091644C31972630 @default.
- W2794091644 hasConceptScore W2794091644C36289849 @default.
- W2794091644 hasConceptScore W2794091644C41008148 @default.
- W2794091644 hasConceptScore W2794091644C41895202 @default.
- W2794091644 hasConceptScore W2794091644C4641261 @default.
- W2794091644 hasConceptScore W2794091644C52622490 @default.
- W2794091644 hasConceptScore W2794091644C54654163 @default.
- W2794091644 hasConceptScore W2794091644C81363708 @default.
- W2794091644 hasLocation W27940916441 @default.
- W2794091644 hasLocation W27940916442 @default.
- W2794091644 hasOpenAccess W2794091644 @default.
- W2794091644 hasPrimaryLocation W27940916441 @default.
- W2794091644 hasRelatedWork W1775397219 @default.
- W2794091644 hasRelatedWork W1982770690 @default.
- W2794091644 hasRelatedWork W2017517155 @default.
- W2794091644 hasRelatedWork W2147083459 @default.
- W2794091644 hasRelatedWork W2353697322 @default.
- W2794091644 hasRelatedWork W2624266381 @default.
- W2794091644 hasRelatedWork W2977314777 @default.
- W2794091644 hasRelatedWork W2995914718 @default.
- W2794091644 hasRelatedWork W3000095492 @default.
- W2794091644 hasRelatedWork W4312603404 @default.
- W2794091644 isParatext "false" @default.
- W2794091644 isRetracted "false" @default.
- W2794091644 magId "2794091644" @default.