{"url":"/sota/facial-expression-recognition-on-fer2013","task":{"name":"Facial Expression Recognition (FER)","url":"/task/facial-expression-recognition","note":null},"dataset":{"name":"FER2013","url":"/dataset/fer2013"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Facial Expression Recognition (FER)** is a computer vision task aimed at identifying and categorizing emotional expressions depicted on a human face. The goal is to automate the process of determining emotions in real-time, by analyzing the various features of a face such as eyebrows, eyes, mouth, and other features, and mapping them to a set of emotions such as anger, fear, surprise, sadness and happiness.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [DeXpression](https://arxiv.org/pdf/1509.05371v2.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":17,"rows_with_code":13,"rows_with_paper_page":17,"rows_dated":17,"rows_using_additional_data":10},"rows":[{"rank_in_archive_order":1,"model":"EfficientFER","metrics":{"Accuracy":"82.47"},"uses_additional_data":true,"paper_date":"2025-06-02","paper":"/paper/efficientfer-efficientnetv2-based-deep","paper_url":"https://ieeexplore.ieee.org/document/11017006","paper_title":"EfficientFER: EfficientNetv2 Based Deep Learning Approach for Facial Expression Recognition","code":"https://github.com/mkonuk66/EfficientFER","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"FERNeXt-SDAFE","metrics":{"Accuracy":"81.33"},"uses_additional_data":true,"paper_date":"2025-04-06","paper":"/paper/sdafe-a-dual-filter-stable-diffusion-data","paper_url":"https://ieeexplore.ieee.org/abstract/document/10888031","paper_title":"SDAFE: A Dual-filter Stable Diffusion Data Augmentation Method for Facial Expression Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"ResEmoteNet","metrics":{"Accuracy":"79.79"},"uses_additional_data":true,"paper_date":"2024-09-01","paper":"/paper/resemotenet-bridging-accuracy-and-loss","paper_url":"https://arxiv.org/abs/2409.10545v2","paper_title":"ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition","code":"https://github.com/ArnabKumarRoy02/ResEmoteNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Ensemble ResMaskingNet with 6 other CNNs","metrics":{"Accuracy":"76.82"},"uses_additional_data":true,"paper_date":"2021-05-05","paper":"/paper/facial-expression-recognition-using-residual","paper_url":"https://ieeexplore.ieee.org/document/9411919","paper_title":"Facial Expression Recognition using Residual Masking Network","code":"https://github.com/phamquiluan/ResidualMaskingNetwork","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Mini-ResEmoteNet (A)","metrics":{"Accuracy":"76.33"},"uses_additional_data":true,"paper_date":"2025-01-30","paper":"/paper/mini-resemotenet-leveraging-knowledge","paper_url":"https://arxiv.org/abs/2501.18538v1","paper_title":"Mini-ResEmoteNet: Leveraging Knowledge Distillation for Human-Centered Design","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"EmoNeXt","metrics":{"Accuracy":"76.12"},"uses_additional_data":false,"paper_date":"2025-01-14","paper":"/paper/emonext-an-adapted-convnext-for-facial-1","paper_url":"https://arxiv.org/abs/2501.08199v1","paper_title":"EmoNeXt: an Adapted ConvNeXt for Facial Emotion Recognition","code":"https://github.com/yelboudouri/EmoNeXt","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"Segmentation VGG-19","metrics":{"Accuracy":"75.97"},"uses_additional_data":true,"paper_date":"2023-03-24","paper":"/paper/a-novel-facial-emotion-recognition-model","paper_url":"https://link.springer.com/article/10.1007/s41870-023-01184-z","paper_title":"A novel facial emotion recognition model using segmentation VGG-19 architecture","code":"https://github.com/VigneshS10/Segmentation-VGG19","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"Local Learning Deep+BOW","metrics":{"Accuracy":"75.42"},"uses_additional_data":true,"paper_date":"2018-04-29","paper":"/paper/local-learning-with-deep-and-handcrafted","paper_url":"https://arxiv.org/abs/1804.10892v7","paper_title":"Local Learning with Deep and Handcrafted Features for Facial Expression Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"LHC-Net","metrics":{"Accuracy":"74.42"},"uses_additional_data":true,"paper_date":"2021-11-14","paper":"/paper/local-multi-head-channel-self-attention-for","paper_url":"https://arxiv.org/abs/2111.07224v2","paper_title":"Local Multi-Head Channel Self-Attention for Facial Expression Recognition","code":"https://github.com/bodhis4ttva/lhc_net","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"Residual Masking Network","metrics":{"Accuracy":"74.14"},"uses_additional_data":true,"paper_date":"2021-05-05","paper":"/paper/facial-expression-recognition-using-residual","paper_url":"https://ieeexplore.ieee.org/document/9411919","paper_title":"Facial Expression Recognition using Residual Masking Network","code":"https://github.com/phamquiluan/ResidualMaskingNetwork","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"ResNet18 With Tricks","metrics":{"Accuracy":"73.70"},"uses_additional_data":false,"paper_date":"2021-12-29","paper":"/paper/fer2013-recognition-resnet18-with-tricks","paper_url":"https://github.com/LetheSec/Fer2013-Recognition-Pytorch/blob/main/README.md","paper_title":"Fer2013 Recognition - ResNet18 With Tricks","code":"https://github.com/LetheSec/Fer2013-Facial-Emotion-Recognition-Pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"VGGNet","metrics":{"Accuracy":"73.28"},"uses_additional_data":false,"paper_date":"2021-05-08","paper":"/paper/facial-emotion-recognition-state-of-the-art","paper_url":"https://arxiv.org/abs/2105.03588v1","paper_title":"Facial Emotion Recognition: State of the Art Performance on FER2013","code":"https://github.com/usef-kh/fer","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"CNN Hyperparameter Optimisation","metrics":{"Accuracy":"72.16"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/convolutional-neural-network-hyperparameters","paper_url":"https://www.semanticscholar.org/paper/Convolutional-Neural-Network-Hyperparameters-for-Vulpe-Grigora%C5%9Fi-Grigore/fe344427eafecc60a1ba29beb87a46e91b7c1420#related-papers","paper_title":"Convolutional Neural Network Hyperparameters optimization for Facial Emotion Recognition","code":"https://github.com/jiantenggei/Convolutional-Neural-Network-Hyperparameters-Optimization-for-Facial-Emotion-Recognition","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"Ad-Corre","metrics":{"Accuracy":"72.03"},"uses_additional_data":false,"paper_date":"2022-03-03","paper":"/paper/ad-corre-adaptive-correlation-based-loss-for","paper_url":"https://ieeexplore.ieee.org/document/9727163","paper_title":"Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild","code":"https://github.com/aliprf/Ad-Corre","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"Mini-ResEmoteNet (B)","metrics":{"Accuracy":"70.20"},"uses_additional_data":true,"paper_date":"2025-01-30","paper":"/paper/mini-resemotenet-leveraging-knowledge","paper_url":"https://arxiv.org/abs/2501.18538v1","paper_title":"Mini-ResEmoteNet: Leveraging Knowledge Distillation for Human-Centered Design","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"DeepEmotion","metrics":{"Accuracy":"70.02"},"uses_additional_data":false,"paper_date":"2019-02-04","paper":"/paper/deep-emotion-facial-expression-recognition","paper_url":"http://arxiv.org/abs/1902.01019v1","paper_title":"Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network","code":"https://github.com/omarsayed7/Deep-Emotion","n_code_links":3,"syntology":null},{"rank_in_archive_order":17,"model":"Local Learning BOW","metrics":{"Accuracy":"67.48"},"uses_additional_data":false,"paper_date":"2013-07-01","paper":"/paper/challenges-in-representation-learning-a","paper_url":"http://arxiv.org/abs/1307.0414v1","paper_title":"Challenges in Representation Learning: A report on three machine learning contests","code":"https://github.com/phamquiluan/ResidualMaskingNetwork","n_code_links":12,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}