Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild

By Shan Li, Weihong Deng, Junping Du. Computer Vision and Pattern Recognition, 2017

1,348 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/714733b70475649320513fa6fa030bd01dd4cd37

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Experimental and Cognitive Psychology

Citations in the corpus

TransFER: Learning Relation-aware Facial Expression Representations with Transformers (2021, background): “Loss functions are designed in [18, 11] to enhance the discriminative ability of expression features.”
Deep Facial Expression Recognition: A Survey (2018, methodology): “RAF-DB [34], [44] 29672 images N/A Internet P & S seven basic expressions and”
Suppressing Uncertainties for Large-Scale Facial Expression Recognition (2020, background): “[22] contains 30,000 facial images annotated with basic or compound expressions by 40 trained human coders.”
FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply (2020, background): “The first four datasets, FER+[20], RAFDB[35], EXPW[53], and AFFECTNET[38] are FER datasets.”
A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, background): “Real-world Affective Face Database (RAF-DB) [87] contains 29,672 highly diverse facial images from the Internet, with manually crowd-sourced annotations (seven basic and eleven compound emotion labels).”
Occlusion Aware Facial Expression Recognition Using CNN With Attention Mechanism (2019, methodology): “1) Datasets: We evaluated the methods on both in-the-wild datasets (RAF-DB [4], AffectNet [5], SFEW [35]) and inthe-lab datasets (CK+ [1], MMI [2], and Oulu-CASIA [3]).”
Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition (2019, background): “[21], [48], [36], [17].”
IExpressNet: Facial Expression Recognition with Incremental Classes (2020, background): “For instance, deep locality preserving learning [35], de-expression residue learning [71], enhanced deep 3D convolutional neural networks [24], and multitask networks [74] are put forward to illustrate these problems.”
Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace (2019, methodology): “In one of them, a best performing network used a locality preserving loss function [22].”
Context-Aware Emotion Recognition Networks (2019, background): “Previous researches for emotion recognition based on handcrafted features [4, 5] or deep networks [6, 7, 8] have mainly focused on the perception of the facial expression, based on the assumption that facial images are one of the most discriminative features of emotional responses.”
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks (2017, background): “nose tip or eye centre, which provides rich geometric information for other face analysis tasks such as face recognition [55, 40, 37, 67], emotion estimation [69, 16, 57, 35] and 3D face reconstruction [15, 31, 26, 25, 48, 33, 19].”
Facial Expression Recognition with Inconsistently Annotated Datasets (2018, background): “RAF[16] contains 12,271 training samples and 3,068 test samples annotated with six basic emotional categories (anger, disgust, fear, happy, sad, surprise) and neutral.”