Browse State-of-the-Art › Facial Expression Recognition (FER)

Facial Expression Recognition (FER)

155 papers with code · 25 benchmarks · 29 datasets archive 2025-07-28

Computer Vision

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.

( Image credit: DeXpression )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

25 leaderboard tables shown for this task, 25 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 25 until expanded.

Syntology 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): AffectNet (1 judged, 0 placed), RAF-DB (1 judged, 0 placed), CREMA-D (1 judged, 0 placed), RAVDESS (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
AffectNet (50 rows) Norface Norface: Improving Facial Expression Analysis by Identity Normalization code — Compare
RAF-DB (35 rows) ResEmoteNet ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial... code — Compare
FER2013 (17 rows) EfficientFER EfficientFER: EfficientNetv2 Based Deep Learning Approach for... code — Compare
FER+ (14 rows) PAtt-Lite PAtt-Lite: Lightweight Patch and Attention MobileNet for... code — Compare
Acted Facial Expressions In The Wild (AFEW) (8 rows) ResNet50 Exploring Emotion Features and Fusion Strategies for Audio-Video... — — Compare
CK+ (7 rows) EmoNeXt A novel deep learning approach for facial emotion recognition:... code — Compare
FERPlus (4 rows) KTN Adaptively Learning Facial Expression Representation via C-F... — — Compare
JAFFE (4 rows) TL Facial Emotion Recognition Using Transfer Learning in the Deep CNN code — Compare
SFEW (4 rows) Ada-DF A Dual-Branch Adaptive Distribution Fusion Framework for... code — Compare
Aff-Wild2 (2 rows) GReFEL GReFEL: Geometry-Aware Reliable Facial Expression Learning under... — — Compare
BP4D (2 rows) Norface Norface: Improving Facial Expression Analysis by Identity Normalization code — Compare
DISFA (2 rows) Norface Norface: Improving Facial Expression Analysis by Identity Normalization code — Compare
FERG (2 rows) DeepEmotion Deep-Emotion: Facial Expression Recognition Using Attentional... code — Compare
MMI (2 rows) DeXpression DeXpression: Deep Convolutional Neural Network for Expression Recognition code — Compare
Oulu-CASIA (2 rows) Dynamic MTL Dynamic Multi-Task Learning for Face Recognition with Facial Expression code — Compare
Real-World Affective Faces (2 rows) Covariance Pooling Covariance Pooling For Facial Expression Recognition code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
Static Facial Expressions in the Wild (2 rows) Covariance Pooling Covariance Pooling For Facial Expression Recognition code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
^(#!@#)(()))****** (1 row) S 100,000 Podcasts: A Spoken English Document Corpus — — Compare
CAER (1 row) EfficientFace Robust Lightweight Facial Expression Recognition Network with... code — Compare
ExpW (1 row) ResEmoteNet ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial... code — Compare
Cohn-Kanade (1 row) Sequential forward selection Greedy Search for Descriptive Spatial Face Features code — Compare
CREMA-D (1 row) EmoAffectNet LSTM In Search of a Robust Facial Expressions Recognition Model: A... code — Compare
RaFD (1 row) ViT + SE Learning Vision Transformer with Squeeze and Excitation for Facial... — — Compare
RAVDESS (1 row) EmoAffectNet LSTM In Search of a Robust Facial Expressions Recognition Model: A... code — Compare
SAVEE (1 row) EmoAffectNet LSTM In Search of a Robust Facial Expressions Recognition Model: A... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

29 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

5 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 492 · with a code link: 155 · where Syntology ran a sample: 18 (15 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (18 of 492 tagged: 15 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)

Page 1 of 5: papers 1 to 100 of 492, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 15 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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