</> Code with Papers by Syntology

Datasets › RAF-DB

RAF-DB (Real-world Affective Faces)

Introduced by Shan Li et al. in Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild1 Jan 2017 archive 2025-07-28

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.

Source: Landmark Guidance Independent Spatio-channel Attention and Complementary Context Information based Facial Expression Recognition Image Source: http://www.whdeng.cn/raf/model1.html

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Facial Expression Recognition (FER) RAF-DB ResEmoteNet Overall Accuracy 94.76 ResEmoteNet: Bridging Accuracy and Loss Reduction in... ArnabKumarRoy02/ResEmoteNet 35 Compare
Facial Expression Recognition (FER) Real-World Affective Faces Covariance Pooling Accuracy 87.0% Covariance Pooling For Facial Expression Recognition d-acharya/CovPoolFER 2 Compare
Facial Expression Recognition RAF-DB ARBEx Overall Accuracy 92.47 ARBEx: Attentive Feature Extraction with Reliability... takihasan/arbex 1 Compare

Papers archive 2025-07-28

30 shown of 34 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 172. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
QCS: Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition 1 1 4 Nov 2024 not harvested
GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution 0 1 21 Oct 2024 not harvested
ExpLLM: Towards Chain of Thought for Facial Expression Recognition 1 1 4 Sep 2024 not harvested
ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition 1 1 1 Sep 2024 not harvested
A Lightweight Model Enhancing Facial Expression Recognition with Spatial Bias and Cosine-Harmony Loss 1 1 1 Aug 2024 not harvested
Norface: Improving Facial Expression Analysis by Identity Normalization 1 1 22 Jul 2024 not harvested
Representation Learning and Identity Adversarial Training for Facial Behavior Understanding 1 1 15 Jul 2024 not harvested
Batch Transformer: Look for Attention in Batch 0 1 5 Jul 2024 not harvested
Joint Training on Multiple Datasets With Inconsistent Labeling Criteria for Facial Expression Recognition 1 1 2 Apr 2024 not harvested
Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond 0 2 2 Jan 2024 not harvested
From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos 2 1 9 Dec 2023 ran 7 of 14 samples (7 unverified)
FerNeXt: Facial Expression Recognition Using ConvNeXt with Channel Attention 1 1 20 Oct 2023 not harvested
A Dual-Direction Attention Mixed Feature Network for Facial Expression Recognition 1 2 25 Aug 2023 not harvested
A Dual-Branch Adaptive Distribution Fusion Framework for Real-World Facial Expression Recognition 1 1 5 May 2023 not harvested
ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression Learning 1 1 2 May 2023 not harvested
POSTER++: A simpler and stronger facial expression recognition network 1 1 28 Jan 2023 not harvested
Multi-Label Compound Expression Recognition: C-EXPR Database & Network 0 1 1 Jan 2023 not harvested
Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition 1 1 11 Dec 2022 not harvested
Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers 0 3 22 Jul 2022 not harvested
Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition 1 1 21 Jul 2022 ran 0 of 1 samples (1 unverified; 1 pointer-only for licence)
MixAugment & Mixup: Augmentation Methods for Facial Expression Recognition 0 1 9 May 2022 not harvested
Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild 1 1 3 Mar 2022 not harvested
Relative Uncertainty Learning for Facial Expression Recognition 1 1 1 Dec 2021 not harvested
Facial Emotion Recognition: A multi-task approach using deep learning 1 1 28 Oct 2021 not harvested
Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition 2 1 15 Sep 2021 not harvested
Learning Deep Global Multi-scale and Local Attention Features for Facial Expression Recognition in the Wild 1 1 5 Jul 2021 not harvested
Robust Lightweight Facial Expression Recognition Network with Label Distribution Training 1 1 18 May 2021 not harvested
Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study 0 1 8 May 2021 not harvested
Facial Expression Recognition in the Wild via Deep Attentive Center Loss 1 1 7 Jan 2021 not harvested
Pyramid With Super Resolution for In-the-Wild Facial Expression Recognition 1 1 17 Jul 2020 not harvested

The full list of 34 is in the JSON twin.

Dataset loaders archive 2025-07-28

d-acharya/CovPoolFERtf

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Facial Expression Recognition (FER)Facial Expression Recognition

License archive 2025-07-28

Custom (non-commercial)

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

Chinese

Variants archive 2025-07-28

  • Real-World Affective Faces
  • RAF-DB

2 variant names, as the archive lists them.

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