Papers › Emotion Separation and Recognition from a Facial Expression by Generating the Poker...

Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers

22 Jul 2022arXiv:2207.11081archive 2025-07-28

Jia Li, Jiantao Nie, Dan Guo, Richang Hong, Meng Wang

Representation learning and feature disentanglement have garnered significant research interest in the field of facial expression recognition (FER). The inherent ambiguity of emotion labels poses challenges for conventional supervised representation learning methods. Moreover, directly learning the mapping from a facial expression image to an emotion label lacks explicit supervision signals for capturing fine-grained facial features. In this paper, we propose a novel FER model, named Poker Face Vision Transformer or PF-ViT, to address these challenges. PF-ViT aims to separate and recognize the disturbance-agnostic emotion from a static facial image via generating its corresponding poker face, without the need for paired images. Inspired by the Facial Action Coding System, we regard an expressive face as the combined result of a set of facial muscle movements on one's poker face (i.e., an emotionless face). PF-ViT utilizes vanilla Vision Transformers, and its components are firstly pre-trained as Masked Autoencoders on a large facial expression dataset without emotion labels, yielding excellent representations. Subsequently, we train PF-ViT using a GAN framework. During training, the auxiliary task of poke face generation promotes the disentanglement between emotional and emotion-irrelevant components, guiding the FER model to holistically capture discriminative facial details. Quantitative and qualitative results demonstrate the effectiveness of our method, surpassing the state-of-the-art methods on four popular FER datasets.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DisentanglementFace GenerationFacial Expression RecognitionFacial Expression Recognition (FER)Representation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Facial Expression Recognition (FER) AffectNet Vit-base + MAE Accuracy (8 emotion) 62.42 #14 of 50 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet ViT-tiny Accuracy (8 emotion) 58.28 #31 of 50 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet ViT-base Accuracy (8 emotion) 57.99 #33 of 50 Archive leaderboard report
Facial Expression Recognition (FER) FER+ Vit-base + MAE Accuracy 90.18 #7 of 14 Archive leaderboard report
Facial Expression Recognition (FER) FER+ ViT-base Accuracy 88.91 #11 of 14 Archive leaderboard report
Facial Expression Recognition (FER) FER+ ViT-tiny Accuracy 88.56 #12 of 14 Archive leaderboard report
Facial Expression Recognition (FER) RAF-DB ViT-base + MAE Overall Accuracy 91.07 #13 of 35 Archive leaderboard report
Facial Expression Recognition (FER) RAF-DB ViT-base Overall Accuracy 87.22 #26 of 35 Archive leaderboard report
Facial Expression Recognition (FER) RAF-DB ViT-tiny Overall Accuracy 87.03 #27 of 35 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamBPEDropoutLabel SmoothingMAEPosition-Wise Feed-Forward LayerSoftmaxTransformerVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections