FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2811322499> ?p ?o ?g. }

• W2811322499 endingPage "123" @default.
• W2811322499 startingPage "106" @default.
• W2811322499 abstract "Facial expression recognition is a topical task. However, very little research investigates subtle expression recognition, which is important for mental activity analysis, deception detection, etc. We address subtle expression recognition through convolutional neural networks (CNNs) by developing multi-task learning (MTL) methods to effectively leverage a side task: facial landmark detection. Existing MTL methods follow a design pattern of shared bottom CNN layers and task-specific top layers. However, the sharing architecture is usually heuristically chosen, as it is difficult to decide which layers should be shared. Our approach is composed of (1) a novel MTL framework that automatically learns which layers to share through optimisation under tensor trace norm regularisation and (2) an invariant representation learning approach that allows the CNN to leverage tasks defined on disjoint datasets without suffering from dataset distribution shift. To advance subtle expression recognition, we contribute a Large-scale Subtle Emotions and Mental States in the Wild database (LSEMSW). LSEMSW includes a variety of cognitive states as well as basic emotions. It contains 176K images, manually annotated with 13 emotions, and thus provides the first subtle expression dataset large enough for training deep CNNs. Evaluations on LSEMSW and 300-W (landmark) databases show the effectiveness of the proposed methods. In addition, we investigate transferring knowledge learned from LSEMSW database to traditional (non-subtle) expression recognition. We achieve very competitive performance on Oulu-Casia NIR&Vis and CK+ databases via transfer learning." @default.
• W2811322499 created "2018-07-10" @default.
• W2811322499 creator A5007032481 @default.
• W2811322499 creator A5016123060 @default.
• W2811322499 creator A5026530953 @default.
• W2811322499 creator A5032395236 @default.
• W2811322499 creator A5063481044 @default.
• W2811322499 creator A5063900505 @default.
• W2811322499 creator A5074492050 @default.
• W2811322499 creator A5075333422 @default.
• W2811322499 creator A5082634513 @default.
• W2811322499 creator A5086486425 @default.
• W2811322499 creator A5087823932 @default.
• W2811322499 date "2018-01-01" @default.
• W2811322499 modified "2023-09-26" @default.
• W2811322499 title "Deep Multi-task Learning to Recognise Subtle Facial Expressions of Mental States" @default.
• W2811322499 cites W1896424170 @default.
• W2811322499 cites W1903399393 @default.
• W2811322499 cites W1958932515 @default.
• W2811322499 cites W1963826206 @default.
• W2811322499 cites W1968015059 @default.
• W2811322499 cites W1981918162 @default.
• W2811322499 cites W1993482030 @default.
• W2811322499 cites W1993551758 @default.
• W2811322499 cites W1998635907 @default.
• W2811322499 cites W2035372623 @default.
• W2811322499 cites W2041616772 @default.
• W2811322499 cites W2045472600 @default.
• W2811322499 cites W2058961190 @default.
• W2811322499 cites W2065180801 @default.
• W2811322499 cites W2078224158 @default.
• W2811322499 cites W2083021723 @default.
• W2811322499 cites W2103943262 @default.
• W2811322499 cites W2117756735 @default.
• W2811322499 cites W2118550318 @default.
• W2811322499 cites W2143104527 @default.
• W2811322499 cites W2145310492 @default.
• W2811322499 cites W2151103428 @default.
• W2811322499 cites W2158198839 @default.
• W2811322499 cites W2159017231 @default.
• W2811322499 cites W2194775991 @default.
• W2811322499 cites W2284800790 @default.
• W2811322499 cites W2295072214 @default.
• W2811322499 cites W2436394355 @default.
• W2811322499 cites W2474575620 @default.
• W2811322499 cites W2490049321 @default.
• W2811322499 cites W2519753233 @default.
• W2811322499 cites W2554268477 @default.
• W2811322499 cites W2587982884 @default.
• W2811322499 cites W2738672149 @default.
• W2811322499 cites W2740020909 @default.
• W2811322499 cites W2746753454 @default.
• W2811322499 cites W2963112684 @default.
• W2811322499 cites W2963623198 @default.
• W2811322499 cites W2963877604 @default.
• W2811322499 cites W2971794874 @default.
• W2811322499 cites W3101998545 @default.
• W2811322499 cites W3103539074 @default.
• W2811322499 cites W4239943352 @default.
• W2811322499 doi "https://doi.org/10.1007/978-3-030-01258-8_7" @default.
• W2811322499 hasPublicationYear "2018" @default.
• W2811322499 type Work @default.
• W2811322499 sameAs 2811322499 @default.
• W2811322499 citedByCount "27" @default.
• W2811322499 countsByYear W28113224992019 @default.
• W2811322499 countsByYear W28113224992020 @default.
• W2811322499 countsByYear W28113224992021 @default.
• W2811322499 countsByYear W28113224992022 @default.
• W2811322499 countsByYear W28113224992023 @default.
• W2811322499 crossrefType "book-chapter" @default.
• W2811322499 hasAuthorship W2811322499A5007032481 @default.
• W2811322499 hasAuthorship W2811322499A5016123060 @default.
• W2811322499 hasAuthorship W2811322499A5026530953 @default.
• W2811322499 hasAuthorship W2811322499A5032395236 @default.
• W2811322499 hasAuthorship W2811322499A5063481044 @default.
• W2811322499 hasAuthorship W2811322499A5063900505 @default.
• W2811322499 hasAuthorship W2811322499A5074492050 @default.
• W2811322499 hasAuthorship W2811322499A5075333422 @default.
• W2811322499 hasAuthorship W2811322499A5082634513 @default.
• W2811322499 hasAuthorship W2811322499A5086486425 @default.
• W2811322499 hasAuthorship W2811322499A5087823932 @default.
• W2811322499 hasBestOaLocation W28113224992 @default.
• W2811322499 hasConcept C108583219 @default.
• W2811322499 hasConcept C119857082 @default.
• W2811322499 hasConcept C150899416 @default.
• W2811322499 hasConcept C153083717 @default.
• W2811322499 hasConcept C153180895 @default.
• W2811322499 hasConcept C154945302 @default.
• W2811322499 hasConcept C162324750 @default.
• W2811322499 hasConcept C187736073 @default.
• W2811322499 hasConcept C195704467 @default.
• W2811322499 hasConcept C2780297707 @default.
• W2811322499 hasConcept C2780451532 @default.
• W2811322499 hasConcept C28006648 @default.
• W2811322499 hasConcept C2987714656 @default.
• W2811322499 hasConcept C31510193 @default.
• W2811322499 hasConcept C41008148 @default.
• W2811322499 hasConcept C81363708 @default.

• next