Matches in SemOpenAlex for { <https://semopenalex.org/work/W3157360070> ?p ?o ?g. }
- W3157360070 endingPage "936" @default.
- W3157360070 startingPage "925" @default.
- W3157360070 abstract "Facial expression recognition (FER) in-the-wild is challenging due to unconstraint settings such as varying head poses, illumination, and occlusions. In addition, the performance of a FER system significantly degrades due to large intra-class variation and inter-class similarity of facial expressions in real-world scenarios. To mitigate these problems, we propose a novel approach, Discriminative Attention-augmented Feature Learning Convolution Neural Network (DAF-CNN), which learns discriminative expression-related representations for FER. Firstly, we develop a 3D attention mechanism for feature refinement which selectively focuses on attentive channel entries and salient spatial regions of a convolution neural network feature map. Moreover, a deep metric loss termed Triplet-Center (TC) loss is incorporated to further enhance the discriminative power of the deeply-learned features with an expression-similarity constraint. It simultaneously minimizes intra-class distance and maximizes inter-class distance to learn both compact and separate features. Extensive experiments have been conducted on two representative facial expression datasets (FER-2013 and SFEW 2.0) to demonstrate that DAF-CNN effectively captures discriminative feature representations and achieves competitive or even superior FER performance compared to state-of-the-art FER methods." @default.
- W3157360070 created "2021-05-10" @default.
- W3157360070 creator A5029844690 @default.
- W3157360070 creator A5048103902 @default.
- W3157360070 creator A5072958451 @default.
- W3157360070 creator A5073079042 @default.
- W3157360070 date "2021-04-29" @default.
- W3157360070 modified "2023-09-25" @default.
- W3157360070 title "Discriminative attention-augmented feature learning for facial expression recognition in the wild" @default.
- W3157360070 cites W171902450 @default.
- W3157360070 cites W1902237438 @default.
- W3157360070 cites W1965868009 @default.
- W3157360070 cites W1981918162 @default.
- W3157360070 cites W2041616772 @default.
- W3157360070 cites W2097117768 @default.
- W3157360070 cites W2103943262 @default.
- W3157360070 cites W2139916508 @default.
- W3157360070 cites W2169931729 @default.
- W3157360070 cites W2243226955 @default.
- W3157360070 cites W2244142460 @default.
- W3157360070 cites W2246249023 @default.
- W3157360070 cites W2251198138 @default.
- W3157360070 cites W2253728219 @default.
- W3157360070 cites W2280370717 @default.
- W3157360070 cites W2307770531 @default.
- W3157360070 cites W2516176725 @default.
- W3157360070 cites W2520774990 @default.
- W3157360070 cites W2550553598 @default.
- W3157360070 cites W2730601341 @default.
- W3157360070 cites W2738672149 @default.
- W3157360070 cites W2752782242 @default.
- W3157360070 cites W2800833042 @default.
- W3157360070 cites W2884585870 @default.
- W3157360070 cites W2908186737 @default.
- W3157360070 cites W2916690307 @default.
- W3157360070 cites W2944523338 @default.
- W3157360070 cites W2960608680 @default.
- W3157360070 cites W2963495494 @default.
- W3157360070 cites W2963712289 @default.
- W3157360070 cites W2963744743 @default.
- W3157360070 cites W2963954913 @default.
- W3157360070 cites W2981413347 @default.
- W3157360070 cites W2983573090 @default.
- W3157360070 cites W2989184171 @default.
- W3157360070 cites W2996100375 @default.
- W3157360070 cites W3000996870 @default.
- W3157360070 cites W3001196836 @default.
- W3157360070 cites W3010305771 @default.
- W3157360070 cites W3029366905 @default.
- W3157360070 cites W3084346048 @default.
- W3157360070 cites W3090779142 @default.
- W3157360070 cites W3099206234 @default.
- W3157360070 cites W3102246728 @default.
- W3157360070 cites W3107028678 @default.
- W3157360070 doi "https://doi.org/10.1007/s00521-021-06045-z" @default.
- W3157360070 hasPublicationYear "2021" @default.
- W3157360070 type Work @default.
- W3157360070 sameAs 3157360070 @default.
- W3157360070 citedByCount "7" @default.
- W3157360070 countsByYear W31573600702022 @default.
- W3157360070 countsByYear W31573600702023 @default.
- W3157360070 crossrefType "journal-article" @default.
- W3157360070 hasAuthorship W3157360070A5029844690 @default.
- W3157360070 hasAuthorship W3157360070A5048103902 @default.
- W3157360070 hasAuthorship W3157360070A5072958451 @default.
- W3157360070 hasAuthorship W3157360070A5073079042 @default.
- W3157360070 hasBestOaLocation W31573600702 @default.
- W3157360070 hasConcept C103278499 @default.
- W3157360070 hasConcept C108583219 @default.
- W3157360070 hasConcept C115961682 @default.
- W3157360070 hasConcept C138885662 @default.
- W3157360070 hasConcept C153180895 @default.
- W3157360070 hasConcept C154945302 @default.
- W3157360070 hasConcept C162324750 @default.
- W3157360070 hasConcept C176217482 @default.
- W3157360070 hasConcept C195704467 @default.
- W3157360070 hasConcept C199360897 @default.
- W3157360070 hasConcept C21547014 @default.
- W3157360070 hasConcept C2776401178 @default.
- W3157360070 hasConcept C2780719617 @default.
- W3157360070 hasConcept C2987714656 @default.
- W3157360070 hasConcept C31510193 @default.
- W3157360070 hasConcept C41008148 @default.
- W3157360070 hasConcept C41895202 @default.
- W3157360070 hasConcept C45347329 @default.
- W3157360070 hasConcept C50644808 @default.
- W3157360070 hasConcept C59404180 @default.
- W3157360070 hasConcept C81363708 @default.
- W3157360070 hasConcept C90559484 @default.
- W3157360070 hasConcept C97931131 @default.
- W3157360070 hasConceptScore W3157360070C103278499 @default.
- W3157360070 hasConceptScore W3157360070C108583219 @default.
- W3157360070 hasConceptScore W3157360070C115961682 @default.
- W3157360070 hasConceptScore W3157360070C138885662 @default.
- W3157360070 hasConceptScore W3157360070C153180895 @default.
- W3157360070 hasConceptScore W3157360070C154945302 @default.
- W3157360070 hasConceptScore W3157360070C162324750 @default.
- W3157360070 hasConceptScore W3157360070C176217482 @default.