Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313132476> ?p ?o ?g. }
- W4313132476 endingPage "2047" @default.
- W4313132476 startingPage "2033" @default.
- W4313132476 abstract "Facial Expression Recognition (FER) has recently emerged as a crucial area in Human-Computer Interaction (HCI) system for understanding the user’s inner state and intention. However, feature- and label-noise constitute the major challenge for FER in the wild due to the ambiguity of facial expressions worsened by low-quality images. To deal with this problem, in this paper, we propose a simple but effective Facial Expression Noise-tolerant Network (FENN) which explores the inter-class correlations for mitigating ambiguity that usually happens between morphologically similar classes. Specifically, FENN leverages a multivariate normal distribution to model such correlations at the final hidden layer of the neural network to suppress the heteroscedastic uncertainty caused by inter-class label noise. Furthermore, the discriminative ability of deep features is weakened by the subtle differences between expressions and the presence of feature noise. FENN utilizes a feature-noise mitigation module to extract compact intra-class feature representations under feature noise while preserving the intrinsic inter-class relationships. We conduct extensive experiments to evaluate the effectiveness of FENN on both original annotated images and synthetic noisy annotated images from RAF-DB, AffectNet, and FERPlus in-the-wild facial expression datasets. The results show that FENN significantly outperforms state-of-the-art FER methods." @default.
- W4313132476 created "2023-01-06" @default.
- W4313132476 creator A5021961966 @default.
- W4313132476 creator A5028665031 @default.
- W4313132476 creator A5037098061 @default.
- W4313132476 creator A5053887138 @default.
- W4313132476 creator A5071943346 @default.
- W4313132476 creator A5082442712 @default.
- W4313132476 date "2023-05-01" @default.
- W4313132476 modified "2023-09-26" @default.
- W4313132476 title "Toward Facial Expression Recognition in the Wild via Noise-Tolerant Network" @default.
- W4313132476 cites W1514928307 @default.
- W4313132476 cites W1772300941 @default.
- W4313132476 cites W1808888563 @default.
- W4313132476 cites W1955857676 @default.
- W4313132476 cites W1972675781 @default.
- W4313132476 cites W2030909430 @default.
- W4313132476 cites W2041616772 @default.
- W4313132476 cites W2063408839 @default.
- W4313132476 cites W2103943262 @default.
- W4313132476 cites W2106580100 @default.
- W4313132476 cites W2481681431 @default.
- W4313132476 cites W2515770085 @default.
- W4313132476 cites W2520774990 @default.
- W4313132476 cites W2614580201 @default.
- W4313132476 cites W2616630373 @default.
- W4313132476 cites W2738672149 @default.
- W4313132476 cites W2745497104 @default.
- W4313132476 cites W2767094803 @default.
- W4313132476 cites W2798583514 @default.
- W4313132476 cites W2896277673 @default.
- W4313132476 cites W2896983363 @default.
- W4313132476 cites W2902598059 @default.
- W4313132476 cites W2904483377 @default.
- W4313132476 cites W2964295764 @default.
- W4313132476 cites W2969985801 @default.
- W4313132476 cites W2979302305 @default.
- W4313132476 cites W2997336602 @default.
- W4313132476 cites W2999025027 @default.
- W4313132476 cites W3003720578 @default.
- W4313132476 cites W3035336958 @default.
- W4313132476 cites W3091476632 @default.
- W4313132476 cites W3093232475 @default.
- W4313132476 cites W3101998545 @default.
- W4313132476 cites W3134941379 @default.
- W4313132476 cites W3156060522 @default.
- W4313132476 cites W3167267673 @default.
- W4313132476 cites W3173685130 @default.
- W4313132476 cites W3173787706 @default.
- W4313132476 cites W3175546442 @default.
- W4313132476 cites W3186421317 @default.
- W4313132476 cites W3187532107 @default.
- W4313132476 cites W3189369550 @default.
- W4313132476 cites W3205640762 @default.
- W4313132476 cites W3206041168 @default.
- W4313132476 cites W3213215111 @default.
- W4313132476 cites W3215121054 @default.
- W4313132476 cites W4242014054 @default.
- W4313132476 cites W4293409613 @default.
- W4313132476 cites W4312823769 @default.
- W4313132476 doi "https://doi.org/10.1109/tcsvt.2022.3220669" @default.
- W4313132476 hasPublicationYear "2023" @default.
- W4313132476 type Work @default.
- W4313132476 citedByCount "0" @default.
- W4313132476 crossrefType "journal-article" @default.
- W4313132476 hasAuthorship W4313132476A5021961966 @default.
- W4313132476 hasAuthorship W4313132476A5028665031 @default.
- W4313132476 hasAuthorship W4313132476A5037098061 @default.
- W4313132476 hasAuthorship W4313132476A5053887138 @default.
- W4313132476 hasAuthorship W4313132476A5071943346 @default.
- W4313132476 hasAuthorship W4313132476A5082442712 @default.
- W4313132476 hasConcept C115961682 @default.
- W4313132476 hasConcept C138885662 @default.
- W4313132476 hasConcept C153180895 @default.
- W4313132476 hasConcept C154945302 @default.
- W4313132476 hasConcept C195704467 @default.
- W4313132476 hasConcept C199360897 @default.
- W4313132476 hasConcept C2776401178 @default.
- W4313132476 hasConcept C2777212361 @default.
- W4313132476 hasConcept C2780522230 @default.
- W4313132476 hasConcept C28490314 @default.
- W4313132476 hasConcept C41008148 @default.
- W4313132476 hasConcept C41895202 @default.
- W4313132476 hasConcept C90559484 @default.
- W4313132476 hasConcept C97931131 @default.
- W4313132476 hasConcept C99498987 @default.
- W4313132476 hasConceptScore W4313132476C115961682 @default.
- W4313132476 hasConceptScore W4313132476C138885662 @default.
- W4313132476 hasConceptScore W4313132476C153180895 @default.
- W4313132476 hasConceptScore W4313132476C154945302 @default.
- W4313132476 hasConceptScore W4313132476C195704467 @default.
- W4313132476 hasConceptScore W4313132476C199360897 @default.
- W4313132476 hasConceptScore W4313132476C2776401178 @default.
- W4313132476 hasConceptScore W4313132476C2777212361 @default.
- W4313132476 hasConceptScore W4313132476C2780522230 @default.
- W4313132476 hasConceptScore W4313132476C28490314 @default.
- W4313132476 hasConceptScore W4313132476C41008148 @default.
- W4313132476 hasConceptScore W4313132476C41895202 @default.