浏览全部资源
扫码关注微信
收稿：2026-05-05，
修回：2026-07-24，
录用：2026-08-10，
网络首发：2026-08-20，
移动端阅览
目的
2
人脸表情识别（Facial Expression Recognition， FER）是人机交互与情感计算领域的核心技术，在智能监控、教育评估和医疗诊断等方面具有广阔的应用前景。近年来，Vision Transformer（ViT）架构凭借其强大的建模能力以及与多模态大模型良好的兼容性，正逐步取代传统卷积神经网络，成为FER领域的研究热点。然而，现有基于ViT的FER方法在预训练与后训练策略的选择上缺乏系统性探究，不同方法间性能差异显著，且原生ViT模型通常难以直接取得优于CNN或混合架构的识别效果。
方法
2
针对上述问题，本文首先系统梳理并实验对比了监督预训练、自监督预训练及多种后训练策略在原生ViT上的适用性。进一步，结合人脸表情识别需捕捉面部细微形变的特性，本文提出一种混合监督对比学习后训练方法，通过在监督对比学习中引入样本混合策略，有效扩展正样本多样性，增强模型对细粒度特征的判别能力。基于系统评估，本文提出掩码图像预训练与混合监督对比学习后训练相结合的原生ViT训练范式MIMIC（Masked Image Pre-training with Mixed Contrastive Learning）。
结果
2
在RAF-DB、AffectNet和FERPlus三个基准数据集上的大量实验表明，MIMIC在不引入任何卷积模块或复杂辅助模块的条件下，显著优于现有训练范式，展现出更强的特征学习能力，并随着模型规模增大，该方法未出现明显性能饱和现象，
结论
2
MIMIC能够有效提升原生ViT在面部表情识别任务中的特征学习能力，在多个数据集上达到当前最优或相当的性能，验证了预训练与后训练协同优化策略对于提升ViT模型FER性能的有效性。（本文相关代码可见
https：//github.com/zfkarl/MIMIC/tree/master/Code_for_MIMIC
https://github.com/zfkarl/MIMIC/tree/master/Code_for_MIMIC
）
Objective
2
Facial expression recognition （FER） is a fundamental technology for understanding human emotions and human-computer interaction， possessing extensive application value across diverse fields such as intelligent surveillance， educational assessment， and healthcare diagnostics. Despite significant advancements driven by deep learning， developing robust FER systems remains a highly challenging endeavor. In uncontrolled real-world environments， the high visual and macroscopic similarity between different emotion categories—where distinguishing features are often confined to subtle local deformations—complicates accurate classification. Historically， the dominant paradigm in FER has heavily relied on Convolutional Neural Networks （CNNs） pretrained in a fully supervised manner on massive facial datasets （e.g.， MS-Celeb-1M）. This conventional paradigm incurs exorbitant costs due to its strict reliance on millions of manually annotated labels. Recently， Vision Transformer （ViT） architectures have emerged as a powerful alternative due to their superior structural capacity and ease of integration with other modalities. However， a critical gap remains： current ViT-based FER methods often exhibit highly variable performance， and purely "plain ViT" models typically underperform compared to hybrid CNN-ViT architectures. We identify that this discrepancy primarily stems from a lack of systematic investigation into the pre-training and post-training strategies specifically tailored for plain ViTs. Therefore， the primary objective of this study is to systematically explore whether plain ViT architectures are inherently suitable for FER tasks， and to formulate an optimal， highly efficient pre-training and post-training paradigm that mitigates domain gaps and enhances fine-grained feature discrimination without relying on complex auxiliary modules.
Methodology
To address the aforementioned challenges， we first co
nduct a comprehensive empirical review of prevalent supervised pre-training， self-supervised pre-training， and post-training paradigms under a unified experimental setting. Our preliminary analysis reveals that simply adopting general visual training paradigms （e.g.， supervised pre-training on ImageNet followed by standard cross-entropy fine-tuning） fails to adequately capture the subtle facial deformations critical for FER. Consequently， we propose an innovative， unified two-stage training framework termed Masked Image Pre-training with Mixed Contrastive Learning （MIMIC） designed exclusively for plain ViT architectures. The first stage focuses on self-supervised representation learning to eliminate annotation reliance. We employ a plain ViT encoder and pre-train it on a mid-scale general image dataset （ImageNet-1K） utilizing a Masked Image Modeling （MIM） task. By randomly masking a high proportion of image patches and optimizing a reconstruction loss to recover the missing pixels， the network is forced to learn highly fine-grained and discriminative visual representations. This self-supervised approach successfully shifts the pre-training data source from domain-specific face datasets to general images， significantly reducing manual annotation costs.The second stage—post-training （fine-tuning）—is specifically designed to bridge the severe domain gap between general images and facial expressions， while simultaneously addressing the high inter-class similarity of human emotions. After discarding the MIM decoder， we adapt the pre-trained ViT encoder for the downstream FER task. Standard cross-entropy loss or traditional supervised contrastive learning （SCL） tends to apply rigid， "hard" positive/negative sample divisions. This rigid grouping inadvertently ignores the valuable discriminative information hidden in samples from different emotion classes that share high visual similarity （e.g.， "happiness" and "neutrality"）. To overcome this， we introduce a novel Mixed Supervised Contrastive Learning （MSCL） strategy. Ba
sed on the standard SCL framework， MSCL incorporates a data mixing strategy （combining Mixup and CutMix techniques with blending coefficients sampled from a Beta distribution） to synthesize augmented images and their corresponding blended labels. These mixed samples are projected into a dense hidden space. Depending on the distance between the synthesized labels and the anchor labels relative to a predefined threshold， the mixed samples are dynamically categorized as soft positive or negative pairs. This substantially expands the diversity of positive samples and enhances the model's capacity to scrutinize subtle facial nuances. The final optimization objective is a balanced combination of the standard classification loss and the MSCL loss.
Results
2
Extensive experiments were conducted on three widely recognized and highly challenging benchmark datasets： RAF-DB， FERPlus， and AffectNet-7. To ensure fair evaluation， a plain ViT-B/16 was employed as the primary backbone. The experimental results conclusively demonstrate that the proposed MIMIC framework consistently exhibits superior feature learning capabilities. When evaluated against strong baselines—including fully supervised approaches， standard contrastive learning methods such as MoCo V3， and conventional masked image modeling techniques like MAE and LocalMIM—MIMIC achieved the highest accuracy across all three datasets. Furthermore， the MIMIC paradigm demonstrates remarkable scalability. When scaling the model size to ViT-L/16， no performance saturation was observed. Specifically， without utilizing any CNN feature extraction modules， additional parameters， or complex relation-aware networks， our plain ViT-L/16 model achieved an outstanding accuracy of 91.26% on the RAF-DB dataset and 91.24% on the FERPlus dataset. These results successfully surpass a wide array of current state-of-the-art hybrid methods， strongly underscoring the untapped potential of pure attention-based architectures in FER. Comprehensive ablation studies further validated our specific architectural and training design choices. For the contrastive loss optimization， utilizing a dense projection head proved significantly more effective than a linear one. Moreover， for bridging cross-domain discrepancies， Global Average Pooling （GAP） was found to be superior to the standard class token. Interestingly， pre-training on the general ImageNet-1K dataset yielded better downstream performance than pre-training on the domain-specific MS-Celeb-1M face dataset， indicating that the superior image diversity of general datasets facilitates more robust representation learning for MIM tasks. Finally， parameter sensitivity analysis confirmed optimal stability at a batch size of 64 and a temperature parameter of 0.07， while t-SNE visualizations of global features intuitively confirmed that the MIMIC strategy achieves exceptionally clear class separation and significantly alleviates instance-level identity confusion compared to traditional supervised training.
Conclusion
2
This study thoroughly validates the innate suitability and immense potential of plain ViT architectures for facial expression recognition. By systematically analyzing the limitations of existing training paradigms， we successfully formulate the MIMIC methodology. By substituting supervised pre-training on massive face datasets with self-supervised masked image pre-training on general datasets， we significantly alleviate the reliance on costly manual annotations. Concurrently， the introduction of the mixed supervised contrastive post-training strategy effectively mitigates severe domain discrepancies and solves the challenge of inter-class similarity by expanding positive sample diversity. The proposed paradigm proves that combining self-supervised general image pre-training with advanced contrastive post-training is a highly viable， robust， and cost-effective pathway for constructing high-performing， pure-attention-based emotion recognition systems. Future research will focus on extending this highly effective training paradigm to broader affective computing domains， such as multimodal emotion recognition and video-based sentiment analysis.
Clavel C ， Vasilescu I ， Devillers L ， Richard G and Ehrette T . 2008 . Fear-type emotion recognition for future audio-based surveillance systems . Speech Communication ， 50 （ 6 ）： 487 - 503
Yang D ， Alsadoon P C ， Prasad P C ， Singh A K and Elchouemi A . 2018 . An emotion recognition model based on facial recognition in virtual learning environment . Procedia Computer Science ， 125 ： 2 - 10
Pioggia G ， Igliozzi R ， Ferro M ， Ahluwalia A ， Muratori F and De Rossi D . 2005 . An android for enhancing social skills and emotion recognition in people with autism . IEEE Transactions on Neural Systems and Rehabilitation Engineering ， 13 （ 4 ）： 507 - 515
Ren F and Quan C . 2012 . Linguistic-based emotion analysis and recognition for measuring consumer satisfaction： an application of affective computing . Information Technology and Management ， 13 （ 4 ）： 321 - 332
Kopalidis T ， Solachidis V ， Vretos N ， Daras P . Advances in facial expression recognition： A survey of methods， benchmarks， models， and datasets . Information ， 2024 ， 15 （ 3 ）： 135
Li S and Deng W . 2020 . Deep facial expression recognition： A survey . IEEE Transactions on Affective Computing
Li S ， Deng W and Du J . 2017 . Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Honolulu ： IEEE： 2852 - 2861
Mao J ， Xu R ， Yin X ， et al . Poster++： A simpler and stronger facial expression recognition network ［J］. Pattern Recognition ， 2025 ， 157 ： 110951 .
Shen Z . A comparative study of hybrid CNN and vision transformer models for facial emotion recognition ［C］// 2024 11th International Conference on Dependable Systems and Their Applications （DSA） . IEEE ， 2024 ： 401 - 408 .
Steiner A. ， Kolesnikov A. ， Zhai X. ， Wightman R. ， Jakobsen J. ， Beyer L. ， Ros H. ， Resnick C. ， Gelly S. ， & Moulin J . 2022 . How to train your ViT？ Data ， augmentation， and regularization in Vision Transformers // Transactions on Machine Learning Research.
Li H ， Wang N ， Ding X ， Yang X and Gao X . 2021 . Adaptively learning facial expression representation via cf labels and distillation . IEEE Transactions on Image Processing ， 30 ： 2016 - 2028
She J ， Hu Y ， Shi H ， Wang J ， Shen Q and Mei T . 2021 . Dive into ambiguity： Latent distribution mining and pairwise uncertainty estimation for facial expression recognition // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville ： IEEE： 6248 - 6257
Jin H ， Jian M ， Ding D and Yu H . 2026 . HMamba-3DFT： A hierarchical mamba framework for emotion-driven semantic 3D facial tracking . Pattern Recognition ， 178 ： 113415 .
Jian M ， Wang R ， Yu X ， Xu F ， Yu H and Lam K M . 2024 . UniFRD： A Unified Method for Facial Image Restoration Based on Diffusion Probabilistic Model . IEEE Transactions on Circuits and Systems for Video Technology ， 34 （ 12 ）： 13494 - 13506 .
Cui X Y ， He C ， Zhao H K and Wang M L . 2024 . Combining ViT with contrastive learning for facial expression recognition . Journal of Image and Graphics ， 29 （ 01 ）： 0123 - 0133
崔鑫宇 ， 何翀 ， 赵宏珂 ， 王美丽 . 2024 . 融合ViT与对比学习的面部表情识别 . 中国图象图形学报 ， 29 （ 01 ）： 0123 - 0133 ［ DOI： 10.11834/jig.230043 http://dx.doi.org/10.11834/jig.230043 ］
Lu L D ， Xia H Y ， Tan Y M and Song S X . 2024 . Attention-guided local feature joint learning for facial expression recognition . Journal of Image and Graphics ， 29 （ 08 ）： 2377 - 2387
卢莉丹 ， 夏海英 ， 谭玉枚 ， 宋树祥 . 2024 . 注意力引导局部特征联合学习的人脸表情识别 . 中国图象图形学报 ， 29 （ 08 ）： 2377 - 2387 ［ DOI： 10.11834/jig.230410 http://dx.doi.org/10.11834/jig.230410 ］
Wang Y J ， He J ， Zhang J X ， Sun R H and Liu X L . 2025 . Semi-supervised facial expression recognition robust to head pose empowered by dual consistency constraints . Journal of Image and Graphics ， 30 （ 02 ）： 0435 - 0450
王宇键 ， 何军 ， 张建勋 ， 孙仁浩 ， 刘学亮 . 2025 . 头姿鲁棒的双一致性约束半监督表情识别 . 中国图象图形学报 ， 30 （ 02 ）： 0435 - 0450 ［ DOI： 10.11834/jig.240205 http://dx.doi.org/10.11834/jig.240205 ］
Xue F ， Wang Q and Guo G . 2021 . Transfer： Learning relation-aware facial expression representations with transformers // Proceedings of the IEEE/CVF International Conference on Computer Vision . Montreal ： IEEE： 3601 - 3610
Tian Y ， Zhu J ， Yao H ， Chen D . 2024 . Facial expression recognition based on Vision Transformer with hybrid local attention . Applied Sciences ， 14 （ 15 ）： 6471 .
Li N ， Huang Y ， Wang Z ， Fan Z ， Li X ， Xiao Z . 2024 . Enhanced hybrid Vision Transformer with multi-scale feature integration and patch dropping for facial expression recognition . Sensors ， 24 （ 13 ）： 4153 .
Zhang Y ， Zheng X ， Liang C ， Hu J ， Deng W . 2024 . Generalizable facial expression recognition // Proceedings of the European Conference on Computer Vision . Cham ： Springer： 231 - 248 .
Tao H and Duan Q . 2023 . Hierarchical attention network with progressive feature fusion for facial expression recognition . Neural Networks
Gao H ， Wu M ， Chen Z ， Li Y ， Wang X and An S ， et al . 2023 . Ssa-icl： Multi-domain adaptive attention with intra-dataset continual learning for facial expression recognition . Neural Networks ， 158 ： 228 - 238
Guo Y ， Zhang L ， Hu Y ， He X and Gao J . 2016 . Ms-celeb-1m： A dataset and benchmark for large-scale face recognition // Computer Vision-ECCV 2016： 14th European Conference . Amsterdam ： Springer： 87 - 102
He K ， Chen X ， Xie S ， Li Y ， Dollar P and Girshick R . 2022 . Masked autoencoders are scalable vision learners // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans ： IEEE： 16000 - 16009
Xie Z ， Zhang Z ， Cao Y ， Lin Y ， Bao J and Yao Z ， et al . 2022 . Simmim： A simple framework for masked image modeling // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans ： IEEE： 9653 - 9663
Gunel B ， Du J ， Conneau A and Stoyanov V . 2021 . Supervised contrastive learning for pre-trained language model fine-tuning ［EB/OL］. ［ 2024-03-29 ］. https://openreview.net/forum?id=cu7IUiOhujH https://openreview.net/forum?id=cu7IUiOhujH
Moukafih Y ， Ghogho M and Smaili K . 2023 . Supervised contrastive learning as multi-objective optimization for fine-tuning large pre-trained language models ［EB/OL］.［ 2024-03-29 ］. https://doi.org/10.1109/ICASSP49357.2023.10095108 https://doi.org/10.1109/ICASSP49357.2023.10095108
He K ， Fan H ， Wu Y ， Xie S and Girshick R . 2020 . Momentum contrast for unsupervised visual representation learning // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle ： IEEE： 9729 - 9738
Chen X ， Fan H ， Girshick R and He K . 2020 . Improved baselines with momentum contrastive learning ［EB/OL］.［ 2024-03-29 ］. https://arxiv.org/pdf/2003.04297.pdf https://arxiv.org/pdf/2003.04297.pdf
Khosla P ， Teterwak P ， Wang C ， Sarna A ， Tian Y and Isola P ， et al . 2020 . Supervised contrastive learning . Advances in Neural Information Processing Systems ， 33 ： 18661 - 18673
Zhang K ， Zhang Z ， Li Z and Qiao Y . 2016 . Joint face detection and alignment using multitask cascaded convolutional networks . IEEE Signal Processing Letters ， 23 （ 10 ）： 1499 - 1503
Amos B ， Ludwiczuk B and Satyanarayanan M . 2016 . Openface： A general-purpose face recognition library with mobile applications . Pittsburgh ： CMU School of Computer Science
Hu Y ， Zeng Z ， Yin L ， Wei X ， Zhou X and Huang T S . 2008 . Multi-view facial expression recognition // Proceedings of the 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition . Amsterdam ： IEEE： 1 - 6
Luo Y ， Wu C M and Zhang Y . 2013 . Facial expression recognition based on fusion feature of pca and lbp with svm . Optik ， 124 （ 17 ）： 2767 - 2770
Lucey P ， Cohn J F ， Kanade T ， Saragih J ， Ambadar Z and Matthews I . 2010 . The extended cohn-kanade dataset （ck+）： A complete dataset for action unit and emotion-specified expression // Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops . San Francisco ： IEEE： 94 - 101
Zhao G ， Huang X ， Taini M ， Li S Z and Pietikainen M . 2011 . Facial expression recognition from near-infrared videos . Image and Vision Computing ， 29 （ 9 ）： 607 - 619
Barsoum E ， Zhang C ， Ferrer C C and Zhang Z . 2016 . Training deep networks for facial expression recognition with crowd-sourced label distribution // Proceedings of the 18th ACM International Conference on Multimodal Interaction . Tokyo ： ACM： 279 - 283
Mollahosseini A ， Hasani B and Mahoor M H . 2017 . Affectnet： A database for facial expression， valence， and arousal computing in the wild . IEEE Transactions on Affective Computing ， 10 （ 1 ）： 18 - 31
Wang K ， Peng X ， Yang J ， Meng D and Qiao Y . 2020 . Region attention networks for pose and occlusion robust facial expression recognition . IEEE Transactions on Image Processing ， 29 ： 4057 - 4069
Li Y ， Zeng J ， Shan S and Chen X . 2018 . Occlusion aware facial expression recognition using cnn with attention mechanism . IEEE Transactions on Image Processing ， 28 （ 5 ）： 2439 - 2450
Wang K ， Peng X ， Yang J ， Lu S and Qiao Y . 2020 . Suppressing uncertainties for large-scale facial expression recognition // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle ： IEEE： 6897 - 6906
Zeng J ， Shan S and Chen X . 2018 . Facial expression recognition with inconsistently annotated datasets // Proceedings of the European Conference on Computer Vision . Munich ： Springer： 222 - 237
Hadsell R ， Chopra S and LeCun Y . 2006 . Dimensionality reduction by learning an invariant mapping // Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . New York ： IEEE： 1735 - 1742
Chen T ， Kornblith S ， Norouzi M and Hinton G . 2020 . A simple framework for contrastive learning of visual representations // Proceedings of the 37th International Conference on Machine Learning . Vienna ： PMLR： 1597 - 1607
Vaswani A ， Shazeer N ， Parmar N ， et al . Attention is all you need . Advances in neural information processing systems ， 2017 ， 30 .
Dosovitskiy A ， Beyer L ， Kolesnikov A ， Weissenborn D ， Zhai X and Unterthiner T ， et al . 2020 . An image is worth 16 x 16 words： Transformers for image recognition at scale ［EB/OL］. ［ 2024-03-29 ］. https://arxiv.org/pdf/2010.11929.pdf https://arxiv.org/pdf/2010.11929.pdf
Liu Z ， Lin Y ， Cao Y ， Hu H ， Wei Y and Zhang Z ， et al . 2021 . Swin transformer： Hierarchical vision transformer using shifted windows // Proceedings of the IEEE/CVF International Conference on Computer Vision . Montreal ： IEEE： 10012 - 10022
Zhang H ， Cissé M ， Dauphin Y N and Lopez-Paz D . 2017 . Mixup： Beyond empirical risk minimization ［EB/OL］.［ 2024-03-29 ］. https://arxiv.org/pdf/1710.09412.pdf https://arxiv.org/pdf/1710.09412.pdf
Yun S ， Han D ， Oh S J ， Chun S ， Choe J and Yoo Y . 2019 . Cutmix： Regularization strategy to train strong classifiers with localizable features // Proceedings of the IEEE/CVF International Conference on Computer Vision . Seoul ： IEEE： 6023 - 6032
Deng J ， Dong W ， Socher R ， Li L J ， Li K and Fei-Fei L . 2009 . Imagenet： A large-scale hierarchical image database // Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition . Miami ： IEEE： 248 - 255
Farzaneh A H and Qi X . 2020 . Discriminant distribution-agnostic loss for facial expression recognition in the wild // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Seattle ： IEEE： 406 - 407
Gera D and Balasubramanian S . 2021 . Landmark guidance independent spatio-channel attention and complementary context information based facial expression recognition . Pattern Recognition Letters ， 145 ： 58 - 66
Zhang Y ， Wang C and Deng W . 2021 . Relative uncertainty learning for facial expression recognition . Advances in Neural Information Processing Systems ， 34 ： 17616 - 17627
Farzaneh A H and Qi X . 2021 . Facial expression recognition in the wild via deep attentive center loss // Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision . Waikoloa ： IEEE： 2402 - 2411
Zhao Z ， Liu Q and Wang S . 2021 . Learning deep global multi-scale and local attention features for facial expression recognition in the wild . IEEE Transactions on Image Processing ， 30 ： 6544 - 6556
Li H ， Sui M ， Zhao F ， Zha Z and Wu F . 2021 . Mvt： mask vision transformer for facial expression recognition in the wild ［EB/OL］.［ 2026-03-29 ］. https://arxiv.org/pdf/2106.04520.pdf https://arxiv.org/pdf/2106.04520.pdf
Ma F ， Sun B and Li S . 2021 . Facial expression recognition with visual transformers and attentional selective fusion . IEEE Transactions on Affective Computing
Zhang Y ， Wang C ， Ling X and Deng W . 2022 . Learn from all： Erasing attention consistency for noisy label facial expression recognition // Computer Vision-ECCV 2022： 17th European Conference . Tel Aviv ： Springer： 418 - 434
Feng L ， Lv J ， Han B ， Xu M ， Niu G and Geng X ， et al . 2020 . Provably consistent partial-label learning . Advances in Neural Information Processing Systems ， 33 ： 10948 - 10960
Wen H ， Cui J ， Hang H ， Liu J ， Wang Y and Lin Z . 2021 . Leveraged weighted loss for partial label learning // Proceedings of the 38th International Conference on Machine Learning . Virtual ： PMLR： 11091 - 11100
Wang H ， Xiao R ， Li Y ， Feng L ， Niu G and Chen G ， et al . 2022 . Pico： Contrastive label disambiguation for partial label learning ［EB/OL］. ［ 2026-03-29 ］. https://arxiv.org/pdf/2201.08984.pdf https://arxiv.org/pdf/2201.08984.pdf
Xue F ， Wang Q ， Tan Z ， Ma Z and Guo G . 2022 . Vision transformer with attentive pooling for robust facial expression recognition . IEEE Transactions on Affective Computing
Chen D ， Wen G ， Li H ， Chen R and Li C . 2023 . Multi-relations aware network for in-the-wild facial expression recognition . IEEE Transactions on Circuits and Systems for Video Technology ， 33 ： 3848 - 3859
Li C ， Li X ， Wang X ， et al . 2023 . Fine-grained associative graph representation for facial expression recognition in the wild . IEEE Transactions on Circuits and Systems for Video Technology ， 34 （ 2 ）： 882 - 896 ［ DOI： 10.1109/TCSVT.2023.3237006 http://dx.doi.org/10.1109/TCSVT.2023.3237006 ］
Liu Y ， Zhang X ， Kauttonen J ， et al . 2022 . Uncertain facial expression recognition via multi-task assisted correction ［EB/OL］. ［ 2024-03-29 ］. https://arxiv.org/abs/2212.07144 https://arxiv.org/abs/2212.07144
Li J ， Nie J ， Guo D ， et al . 2025 . Emotion separation and recognition from a facial expression by generating the poker face with vision transformers . IEEE Transactions on Computational Social Systems ， 12 （ 4 ）： 1548 - 1562 ［ DOI： 10.1109/TCSS.2024.3478839 http://dx.doi.org/10.1109/TCSS.2024.3478839 ］
Chen X and Huang L . 2024 . A lightweight model enhancing facial expression recognition with spatial bias and cosine-harmony loss . Computation ， 12 （ 10 ）： 201 ［ DOI： 10.3390/computation12100201 http://dx.doi.org/10.3390/computation12100201 ］
Liu S ， Xu Y ， Wan T and Zheng Z . 2023 . Ada-DF： an adaptive label distribution fusion network for facial expression recognition . IEEE Transactions on Multimedia ， 25 ： 6414 - 6426 ［ DOI： 10.1109/TMM.2022.3210960 http://dx.doi.org/10.1109/TMM.2022.3210960 ］
Song J ， He M ， Feng J ， et al . 2024 . Bridging the gaps： utilizing unlabeled face recognition datasets to boost semi-supervised facial expression recognition ［EB/OL］. ［ 2024-03-29 ］. https://arxiv.org/abs/2410.17622 https://arxiv.org/abs/2410.17622
Liu T ， Li J ， Wu J ， Du B ， Zhan Y ， Tao D and Wan J . 2025 . Facial expression recognition with heatmap neighbor contrastive learning . IEEE Transactions on Multimedia ， 27 ： 4795 - 4807 ［ DOI： 10.1109/TMM.2025.3543029 http://dx.doi.org/10.1109/TMM.2025.3543029 ］
El-Khashab O ， Hamdy A and Mahmoud A . 2023 . FerNeXt： facial expression recognition using ConvNeXt with channel attention // Proceedings of the 2023 International Mobile， Intelligent， and Ubiquitous Computing Conference （MIUCC） . Cairo， Egypt ： IEEE： 1 - 8 ［ DOI： 10.1109/MIUCC58832.2023.10278345 http://dx.doi.org/10.1109/MIUCC58832.2023.10278345 ］
Yu G . 2025 . A multi-granularity feature fusion approach with attention for facial expression recognition . Scientific Reports ， 15 （ 1 ）： 42507 ［ DOI： 10.1038/s41598-025-26533-9 http://dx.doi.org/10.1038/s41598-025-26533-9 ］
Pazandeh A M and Fatemizadeh E . 2025 . Enhancing vision transformers for facial expression recognition . IEEE Access ， 13 ： 144689 - 144698 ［ DOI： 10.1109/ACCESS.2025.3598917 http://dx.doi.org/10.1109/ACCESS.2025.3598917 ］
Song D and Liu C . 2025 . A facial expression recognition network using hybrid feature extraction . PLOS ONE ， 20 （ 1 ）： e 0312359 ［ DOI： 10.1371/journal.pone.0312359 http://dx.doi.org/10.1371/journal.pone.0312359 ］
Devasena G and Vidhya V . 2025 . Twinned attention network for occlusion-aware facial expression recognition . Machine Vision and Applications ， 36 （ 1 ）： 23 ［ DOI： 10.1007/s00138-024-01641-0 http://dx.doi.org/10.1007/s00138-024-01641-0 ］
Chen X ， Xie S and He K . 2021 . An empirical study of training self-supervised vision transformers ［EB/OL］.［ 2026-03-29 ］. https://arxiv.org/pdf/2104.02057.pdf https://arxiv.org/pdf/2104.02057.pdf
Wang H ， Tang Y ， Wang Y ， Guo J ， Deng Z H and Han K . 2023 . Masked image modeling with local multi-scale reconstruction // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Vancouver ： IEEE： 2122 - 2131
Van der Maaten L and Hinton G . 2008 . Visualizing data using t-sne . Journal of Machine Learning Research ， 9 （ 11 ）
相关作者
相关机构
京公网安备11010802024621
