{"url":"/dataset/raf-db","name":"RAF-DB","full_name":"Real-world Affective Faces","description_markdown":"The **Real-world Affective Faces** Database (**RAF-DB**) is a dataset for facial expression. It contains 29672 facial images tagged with basic or compound expressions by 40 independent taggers. Images in this database are of great variability in subjects' age, gender and ethnicity, head poses, lighting conditions, occlusions, (e.g. glasses, facial hair or self-occlusion), post-processing operations (e.g. various filters and special effects), etc.\r\n\r\nSource: [Landmark Guidance Independent Spatio-channel Attention and Complementary Context Information based Facial Expression Recognition](https://arxiv.org/abs/2007.10298)\r\nImage Source: [http://www.whdeng.cn/raf/model1.html](http://www.whdeng.cn/raf/model1.html)","description_withheld":null,"homepage":"http://www.whdeng.cn/raf/model1.html","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/reliable-crowdsourcing-and-deep-locality","title":"Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild","first_author":"Shan Li","url":null},"license":{"name":"Custom (non-commercial)","url":"http://www.whdeng.cn/raf/model1.html#:~:Terms%20&%20Conditions"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Facial Expression Recognition (FER)","url":"/task/facial-expression-recognition","datasets_with_task":"/datasets/task/facial-expression-recognition"},{"name":"Facial Expression Recognition","url":"/task/facial-expression-recognition-1","datasets_with_task":"/datasets/task/facial-expression-recognition-1"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Real-World Affective Faces","RAF-DB"],"data_loaders":[{"repo":"https://github.com/d-acharya/CovPoolFER","url":"https://github.com/d-acharya/CovPoolFER","frameworks":["tf"]}],"num_papers_in_archive":172,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/facial-expression-recognition-on-raf-db","task":"Facial Expression Recognition (FER)","dataset_variant":"RAF-DB","rows":35,"metrics":["Overall Accuracy","Avg. Accuracy"],"first_row_in_archive_order":{"model":"ResEmoteNet","paper":"/paper/resemotenet-bridging-accuracy-and-loss","metrics":{"Overall Accuracy":"94.76"},"code_links":[{"title":"ArnabKumarRoy02/ResEmoteNet","url":"https://github.com/ArnabKumarRoy02/ResEmoteNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/facial-expression-recognition-on-real-world","task":"Facial Expression Recognition (FER)","dataset_variant":"Real-World Affective Faces","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Covariance Pooling","paper":"/paper/covariance-pooling-for-facial-expression","metrics":{"Accuracy":"87.0%"},"code_links":[{"title":"d-acharya/CovPoolFER","url":"https://github.com/d-acharya/CovPoolFER"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/facial-expression-recognition-on-raf-db-1","task":"Facial Expression Recognition","dataset_variant":"RAF-DB","rows":1,"metrics":["Overall Accuracy"],"first_row_in_archive_order":{"model":"ARBEx","paper":"/paper/arbex-attentive-feature-extraction-with","metrics":{"Overall Accuracy":"92.47"},"code_links":[{"title":"takihasan/arbex","url":"https://github.com/takihasan/arbex"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/qcs-feature-refining-from-quadruplet-cross","title":"QCS: Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition","date":"2024-11-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/grefel-geometry-aware-reliable-facial","title":"GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution","date":"2024-10-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/expllm-towards-chain-of-thought-for-facial","title":"ExpLLM: Towards Chain of Thought for Facial Expression Recognition","date":"2024-09-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/resemotenet-bridging-accuracy-and-loss","title":"ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition","date":"2024-09-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-lightweight-model-enhancing-facial","title":"A Lightweight Model Enhancing Facial Expression Recognition with Spatial Bias and Cosine-Harmony Loss","date":"2024-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/norface-improving-facial-expression-analysis","title":"Norface: Improving Facial Expression Analysis by Identity Normalization","date":"2024-07-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/representation-learning-and-identity","title":"Representation Learning and Identity Adversarial Training for Facial Behavior Understanding","date":"2024-07-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/batch-transformer-look-for-attention-in-batch","title":"Batch Transformer: Look for Attention in Batch","date":"2024-07-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/joint-training-on-multiple-datasets-with","title":"Joint Training on Multiple Datasets With Inconsistent Labeling Criteria for Facial Expression Recognition","date":"2024-04-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/distribution-matching-for-multi-task-learning","title":"Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond","date":"2024-01-02","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/from-static-to-dynamic-adapting-landmark-1","title":"From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos","date":"2023-12-09","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":14,"samples_ran":7,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fernext-facial-expression-recognition-using","title":"FerNeXt: Facial Expression Recognition Using ConvNeXt with Channel Attention","date":"2023-10-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-dual-direction-attention-mixed-feature","title":"A Dual-Direction Attention Mixed Feature Network for Facial Expression Recognition","date":"2023-08-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-dual-branch-adaptive-distribution-fusion","title":"A Dual-Branch Adaptive Distribution Fusion Framework for Real-World Facial Expression Recognition","date":"2023-05-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/arbex-attentive-feature-extraction-with","title":"ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression Learning","date":"2023-05-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/poster-v2-a-simpler-and-stronger-facial","title":"POSTER++: A simpler and stronger facial expression recognition network","date":"2023-01-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-label-compound-expression-recognition-c","title":"Multi-Label Compound Expression Recognition: C-EXPR Database & Network","date":"2023-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vision-transformer-with-attentive-pooling-for","title":"Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition","date":"2022-12-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/facial-expression-recognition-using-vanilla","title":"Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers","date":"2022-07-22","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/learn-from-all-erasing-attention-consistency","title":"Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition","date":"2022-07-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mixaugment-mixup-augmentation-methods-for","title":"MixAugment & Mixup: Augmentation Methods for Facial Expression Recognition","date":"2022-05-09","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ad-corre-adaptive-correlation-based-loss-for","title":"Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild","date":"2022-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/relative-uncertainty-learning-for-facial","title":"Relative Uncertainty Learning for Facial Expression Recognition","date":"2021-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/facial-emotion-recognition-a-multi-task","title":"Facial Emotion Recognition: A multi-task approach using deep learning","date":"2021-10-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/distract-your-attention-multi-head-cross","title":"Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition","date":"2021-09-15","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learning-deep-global-multi-scale-and-local","title":"Learning Deep Global Multi-scale and Local Attention Features for Facial Expression Recognition in the Wild","date":"2021-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/robust-lightweight-facial-expression","title":"Robust Lightweight Facial Expression Recognition Network with Label Distribution Training","date":"2021-05-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/distribution-matching-for-heterogeneous-multi","title":"Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study","date":"2021-05-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/facial-expression-recognition-in-the-wild-via","title":"Facial Expression Recognition in the Wild via Deep Attentive Center Loss","date":"2021-01-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pyramid-with-super-resolution-for-in-the-wild","title":"Pyramid With Super Resolution for In-the-Wild Facial Expression Recognition","date":"2020-07-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/expression-affect-action-unit-recognition-aff","title":"Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace","date":"2019-09-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/region-attention-networks-for-pose-and","title":"Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition","date":"2019-05-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/generating-faces-for-affect-analysis","title":"Deep Neural Network Augmentation: Generating Faces for Affect Analysis","date":"2018-11-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/covariance-pooling-for-facial-expression","title":"Covariance Pooling For Facial Expression Recognition","date":"2018-05-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":3,"samples_harvested":16,"samples_ran":8,"samples_unverified":8,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}