Browse State-of-the-Art › Action Unit Detection
Action Unit Detection
16 papers with code · 1 benchmark · 3 datasets archive 2025-07-28
Action unit detection is the task of detecting action units from a video - for example, types of facial action units (lip tightening, cheek raising) from a video of a face.
( Image credit: AU R-CNN )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| BP4D (1 row) | AU R-CNN | AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action... | 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
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 108 · with a code link: 16 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 108 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 108, 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.
-
10 Feb 2020 3 repositories listed Syntology official (archive's flag): 1 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)We use the soft labels and the ground truth to train the student model.
-
15 Aug 2023 2 repositories listedAnatomically, there are innumerable correlations between AUs, which contain rich information and are vital for AU detection.
-
10 Jun 2022 2 repositories listedIn this paper, we consider the problem of real-time video-based facial emotion analytics, namely, facial expression recognition, prediction of valence and arousal and detection of action unit points.
-
14 Dec 2018 2 repositories listed(2) We integrate various dynamic models (including convolutional long short-term memory, two stream network, conditional random field, and temporal action localization network) into AU R-CNN and then investigate and…
-
27 Nov 2018 2 repositories listed Syntology 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)Most of the existing work on automatic facial expression analysis focuses on discrete emotion recognition, or facial action unit detection.
-
1 Jun 2016 2 repositories listedRegion learning (RL) and multi-label learning (ML) have recently attracted increasing attentions in the field of facial Action Unit (AU) detection.
-
2 Oct 2024 1 repository listedSpecifically, we explore the mechanism of self-attention weight distribution, in which the self-attention weight distribution of each AU is regarded as spatial distribution and is adaptively learned under the constraint…
-
4 Aug 2024 1 repository listedEvaluating affect analysis methods presents challenges due to inconsistencies in database partitioning and evaluation protocols, leading to unfair and biased results.
-
9 Feb 2024 1 repository listedFor the Facial Action Unit (AU) detection task, accurately capturing the subtle facial differences between distinct AUs is essential for reliable detection.
-
23 Aug 2023 1 repository listedThe proposed FG-Net achieves a strong generalization ability for heatmap-based AU detection thanks to the generalizable and semantic-rich features extracted from the pre-trained generative model.
-
16 Mar 2023 1 repository listedIn this article, the results of our team for the fifth Affective Behavior Analysis in-the-wild (ABAW) competition are presented.
-
18 Mar 2020 1 repository listedMoreover, to extract precise local features, we propose an adaptive attention learning module to refine the attention map of each AU adaptively.
-
1 Jun 2019 1 repository listedIn this paper, we aim to learn discriminative representation for facial action unit (AU) detection from large amount of videos without manual annotations.
-
25 Mar 2019 1 repository listedDue to the combination of source AU-related information and target AU-free information, the latent feature domain with transferred source label can be learned by maximizing the target-domain AU detection performance.
-
15 Mar 2018 1 repository listedFacial action unit (AU) detection and face alignment are two highly correlated tasks since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection.
-
25 Apr 2017 1 repository listedWe then move to the novel setup of the FERA 2017 Challenge, in which we propose a multi-view extension of our approach that operates by first predicting the viewpoint from which the video was taken, and then evaluating…
-
FG 2025 TrustFAA: the First Workshop on Towards Trustworthy Facial Affect Analysis: Advancing Insights of Fairness, Explainability, and Safety (TrustFAA)5 Jun 2025 0 repositories listedWith the increasing prevalence and deployment of Emotion AI-powered facial affect analysis (FAA) tools, concerns about the trustworthiness of these systems have become more prominent.
-
Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning9 Apr 2025 0 repositories listedThe human face plays a central role in social communication, necessitating the use of performant computer vision tools for human-centered applications.
-
AU-TTT: Vision Test-Time Training model for Facial Action Unit Detection30 Mar 2025 0 repositories listedFacial Action Units (AUs) detection is a cornerstone of objective facial expression analysis and a critical focus in affective computing.
-
Detecting Localized Deepfake Manipulations Using Action Unit-Guided Video Representations28 Mar 2025 0 repositories listedWith rapid advancements in generative modeling, deepfake techniques are increasingly narrowing the gap between real and synthetic videos, raising serious privacy and security concerns.
-
Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection12 Mar 2025 0 repositories listedDespite the impressive performance of current vision-based facial action unit (AU) detection approaches, they are heavily susceptible to the variations across different domains and the cross-domain AU detection methods…
-
Behaviour4All: in-the-wild Facial Behaviour Analysis Toolkit26 Sep 2024 0 repositories listedIn this paper, we introduce Behavior4All, a comprehensive, open-source toolkit for in-the-wild facial behavior analysis, integrating Face Localization, Valence-Arousal Estimation, Basic Expression Recognition and Action…
-
Affective Behavior Analysis using Task-adaptive and AU-assisted Graph Network16 Jul 2024 0 repositories listedIn this paper, we present our solution and experiment result for the Multi-Task Learning Challenge of the 7th Affective Behavior Analysis in-the-wild(ABAW7) Competition.
-
Multi-Task Learning for Affect Analysis30 Jun 2024 0 repositories listedThis Project was my Undergraduate Final Year dissertation, supervised by Dimitrios Kollias This research delves into the realm of affective computing for image analysis, aiming to enhance the efficiency and…
-
Task-adaptive Q-Face15 May 2024 0 repositories listedAlthough face analysis has achieved remarkable improvements in the past few years, designing a multi-task face analysis model is still challenging.
-
AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts20 Mar 2024 0 repositories listedLeveraging the synergy of both audio data and visual data is essential for understanding human emotions and behaviors, especially in in-the-wild setting.
-
Leveraging Synthetic Data for Generalizable and Fair Facial Action Unit Detection15 Mar 2024 0 repositories listedFacial action unit (AU) detection is a fundamental block for objective facial expression analysis.
-
Contrastive Learning of Person-independent Representations for Facial Action Unit Detection6 Mar 2024 0 repositories listedFacial action unit (AU) detection, aiming to classify AU present in the facial image, has long suffered from insufficient AU annotations.
-
The 6th Affective Behavior Analysis in-the-wild (ABAW) Competition29 Feb 2024 0 repositories listedThis paper describes the 6th Affective Behavior Analysis in-the-wild (ABAW) Competition, which is part of the respective Workshop held in conjunction with IEEE CVPR 2024.
-
2 Jan 2024 0 repositories listedMulti-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer.
-
Boosting Facial Action Unit Detection Through Jointly Learning Facial Landmark Detection and Domain Separation and Reconstruction8 Oct 2023 0 repositories listed
-
Occlusion Aware Student Emotion Recognition based on Facial Action Unit Detection18 Jul 2023 0 repositories listed
-
Fighting over-fitting with quantization for learning deep neural networks on noisy labels21 Mar 2023 0 repositories listed
-
Multi-modal Facial Action Unit Detection with Large Pre-trained Models for the 5th Competition on Affective Behavior Analysis in-the-wild19 Mar 2023 0 repositories listed
-
ABAW : Facial Expression Recognition in the wild17 Mar 2023 0 repositories listed
-
Local Region Perception and Relationship Learning Combined with Feature Fusion for Facial Action Unit Detection15 Mar 2023 0 repositories listed
-
Self-supervised Facial Action Unit Detection with Region and Relation Learning10 Mar 2023 0 repositories listed
-
Fighting noise and imbalance in Action Unit detection problems6 Mar 2023 0 repositories listed
-
ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges2 Mar 2023 0 repositories listed
-
Biomechanics-Guided Facial Action Unit Detection Through Force Modeling1 Jan 2023 0 repositories listed
-
ReactioNet: Learning High-Order Facial Behavior from Universal Stimulus-Reaction by Dyadic Relation Reasoning1 Jan 2023 0 repositories listed
-
Uncertain Facial Expression Recognition via Multi-task Assisted Correction14 Dec 2022 0 repositories listed
-
FAN-Trans: Online Knowledge Distillation for Facial Action Unit Detection11 Nov 2022 0 repositories listed
-
Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation28 Oct 2022 0 repositories listed
-
Global-to-local Expression-aware Embeddings for Facial Action Unit Detection27 Oct 2022 0 repositories listed
-
Multimodal Channel-Mixing: Channel and Spatial Masked AutoEncoder on Facial Action Unit Detection25 Sep 2022 0 repositories listed
-
Affective Behavior Analysis using Action Unit Relation Graph and Multi-task Cross Attention21 Jul 2022 0 repositories listed
-
ABAW: Learning from Synthetic Data & Multi-Task Learning Challenges3 Jul 2022 0 repositories listed
-
Cross-subject Action Unit Detection with Meta Learning and Transformer-based Relation Modeling18 May 2022 0 repositories listed
-
An Ensemble Approach for Facial Expression Analysis in Video24 Mar 2022 0 repositories listed
-
Multi-modal Multi-label Facial Action Unit Detection with Transformer24 Mar 2022 0 repositories listed
-
An Attention-based Method for Action Unit Detection at the 3rd ABAW Competition23 Mar 2022 0 repositories listed
-
Multi-label Transformer for Action Unit Detection23 Mar 2022 0 repositories listed
-
Transformer-based Multimodal Information Fusion for Facial Expression Analysis23 Mar 2022 0 repositories listed
-
Multi-Modal Learning for AU Detection Based on Multi-Head Fused Transformers22 Mar 2022 0 repositories listed
-
ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challenges22 Feb 2022 0 repositories listed
-
Multi-Order Networks for Action Unit Detection1 Feb 2022 0 repositories listed
-
Choose Settings Carefully: Comparing Action Unit detection at Different Settings Using a Large-Scale Dataset16 Nov 2021 0 repositories listed
-
Which CNNs and Training Settings to Choose for Action Unit Detection? A Study Based on a Large-Scale Dataset16 Nov 2021 0 repositories listed
-
Action Unit Detection with Joint Adaptive Attention and Graph Relation9 Jul 2021 0 repositories listed
-
Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection19 Jun 2021 0 repositories listed
-
Facial Action Unit Detection With Transformers19 Jun 2021 0 repositories listed
-
Hybrid Message Passing With Performance-Driven Structures for Facial Action Unit Detection19 Jun 2021 0 repositories listed
-
Analysing Affective Behavior in the second ABAW2 Competition14 Jun 2021 0 repositories listed
-
Meta Auxiliary Learning for Facial Action Unit Detection14 May 2021 0 repositories listed
-
8 May 2021 0 repositories listed
-
Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework29 Mar 2021 0 repositories listed
-
PIAP-DF: Pixel-Interested and Anti Person-Specific Facial Action Unit Detection Net With Discrete Feedback Learning1 Jan 2021 0 repositories listed
-
Objective Class-based Micro-Expression Recognition through Simultaneous Action Unit Detection and Feature Aggregation24 Dec 2020 0 repositories listed
-
Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition1 Dec 2020 0 repositories listed
-
Computational efficient deep neural network with difference attention maps for facial action unit detection24 Nov 2020 0 repositories listed
-
Impact of Action Unit Occurrence Patterns on Detection15 Oct 2020 0 repositories listed
-
HiCOMEX: Facial Action Unit Recognition Based on Hierarchy Intensity Distribution and COMEX Relation Learning23 Sep 2020 0 repositories listed
-
Facial movement synergies and Action Unit detection from distal wearable Electromyography and Computer Vision20 Aug 2020 0 repositories listed
-
Multi-label Learning with Missing Values using Combined Facial Action Unit Datasets17 Aug 2020 0 repositories listed
-
Facial Action Unit Detection using 3D Facial Landmarks17 May 2020 0 repositories listed
-
Facial Action Unit Detection on ICU Data for Pain Assessment24 Apr 2020 0 repositories listed
-
Unique Class Group Based Multi-Label Balancing Optimizer for Action Unit Detection5 Mar 2020 0 repositories listed
-
Upper, Middle and Lower Region Learning for Facial Action Unit Detection10 Feb 2020 0 repositories listed
-
Multi-Label Class Balancing Algorithm for Action Unit Detection8 Feb 2020 0 repositories listed
-
Analysing Affective Behavior in the First ABAW 2020 Competition30 Jan 2020 0 repositories listed
-
Facial Action Unit Detection via Adaptive Attention and Relation5 Jan 2020 0 repositories listed
-
Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection23 Oct 2019 0 repositories listed
-
Fast and Effective Adaptation of Facial Action Unit Detection Deep Model26 Sep 2019 0 repositories listed
-
25 Sep 2019 0 repositories listed
-
Micro-expression Action Unit Detection with Spatio-temporal Adaptive Pooling11 Jul 2019 0 repositories listed
-
Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection1 Jun 2019 0 repositories listed
-
Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection8 Apr 2019 0 repositories listed
-
Facial Action Unit Detection Using Attention and Relation Learning10 Aug 2018 0 repositories listed
-
Transfer Learning for Action Unit Recognition19 Jul 2018 0 repositories listed
-
Expression Empowered ResiDen Network for Facial Action Unit Detection13 Jun 2018 0 repositories listed
-
The Intelligent ICU Pilot Study: Using Artificial Intelligence Technology for Autonomous Patient Monitoring25 Apr 2018 0 repositories listed
-
Accurate Facial Parts Localization and Deep Learning for 3D Facial Expression Recognition4 Mar 2018 0 repositories listed
-
Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing10 Apr 2017 0 repositories listed
-
Learning with Privileged Information for Multi-Label Classification29 Mar 2017 0 repositories listed
-
EAC-Net: A Region-based Deep Enhancing and Cropping Approach for Facial Action Unit Detection9 Feb 2017 0 repositories listed
-
Modeling Spatial and Temporal Cues for Multi-label Facial Action Unit Detection2 Aug 2016 0 repositories listed
-
Confidence-Weighted Local Expression Predictions for Occlusion Handling in Expression Recognition and Action Unit detection21 Jul 2016 0 repositories listed
-
1 Jun 2016 0 repositories listed
-
An Empirical Study of Dimensional Reduction Techniques for Facial Action Units Detection25 Mar 2016 0 repositories listed
Syntology lines on 2 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