The DOI matches its Crossref record; 31 of the 32 references it cites were found in a registry or an index.
Static facial expression analysis in tough conditions: Data, evaluation protocol and benchmark
Abstract
Quality data recorded in varied realistic environments is vital for effective human face related research. Currently available datasets for human facial expression analysis have been generated in highly controlled lab environments. We present a new static facial expression database Static Facial Expressions in the Wild (SFEW) extracted from a temporal facial expressions database Acted Facial Expressions in the Wild (AFEW) [9], which we have extracted from movies. In the past, many robust methods have been reported in the literature. However, these methods have been experimented on different databases or using different protocols within the same databases. The lack of a standard protocol makes it difficult to compare systems and acts as a hindrance in the progress of the field. Therefore, we propose a person independent training and testing protocol for expression recognition as part of the BEFIT workshop. Further, we compare our dataset with the JAFFE and Multi-PIE datasets and provide baseline results.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Some of the approaches use predesigned representations [194], [262], [263], [264], [265] while recent successful approaches learn the best representation [146], [147], [152] or combine predesigned and learned features [108].”
From Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-Related Applications (2016) · cites this paper as [194]
In the citing paper
“While approaches to FE detection in naturalistic environments using static representations exist [194], [262], dynamic representations are dominant [108], [113], [146], [147], [263], [264].”
From Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-Related Applications (2016) · cites this paper as [194]
Citations
Cites
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
Ojala, T., Pietikainen, M., & Maenpaa, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1017623 · Cited by 15,398
Libsvm : A library for support vector machines
Ferrari, V. (2008) · Medical Entomology and Zoology · Cited by 10,123
Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
Huang, G. B., Mattar, M., Berg, T. L., & Miller, E. G. (2008) · HAL · Cited by 4,445
A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions
Zeng, Z., Pantic, M., Roisman, G. I., & Huang, T. S. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.52 · Cited by 2,797
Coding facial expressions with Gabor wavelets
Lyons, M. J., Akamatsu, S., Kamachi, M., & Gyoba, J. (2002) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/afgr.1998.670949 · Cited by 2,214
The CMU pose, illumination, and expression database
Sim, T., Baker, S., & Bsat, M. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1251154 · Cited by 1,786
Representing shape with a spatial pyramid kernel
Bosch, A., Zisserman, A., & Muñoz, X. (2007) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1282280.1282340 · Cited by 1,423
Research works printed but not linked: 1
- dhall, 2011, Acted Facial Expressions in the Wild Database
Cited by
Sorted by citations
Items 501–541 of 541
SAST: a suppressing ambiguity self-training framework for facial expression recognition
Guo, Z., Wei, B., Liu, X., Zhang, Z., Liu, S., & Fan, Y. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17749-w
“…four representative and challenging facial expression datasets in our experiments, namely: RAF-DB [34], FERPlus [35], AffectNet [36] and SFEW [37] Weusedthe PyTorch [38] framework to implement SAST with ResNet-18 [39] pretrained on MS-Celeb-1M as the backbone, and trained 512 epochs on an…”
Benchmarking Facial Emotion Recognition Models Using Deep Learning: A Comparative Study
Singh, E., & Nand, P. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-8661-3_8
Ahmad, A. S., hassan, R. B., Zakaria, N. H., Sim, H. M., Shafei, M. L. M., Khairuddin, A. R., & Kasim, S. B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4879048
A cognitive strategy for service robots in recognizing emotional attribute of objects
Wu, H., Du, J., Qin, C., & Ma, Q. (2024) · Artificial Life and Robotics · doi:10.1007/s10015-024-00960-9
Review on Facial Emotion Recognition Using Deep Learning With Multiple Databases
Prasad, M. H., Swarnalatha, P., Anantharajah, K., & Prabu, S. (2024) · Advances in medical technologies and clinical practice book series · doi:10.4018/979-8-3693-3719-6.ch018
MFNet: Mixed Feature Network for Enhancing Facial Emotion Recognition on the Small-Scale Dataset
Chen, H. (2024) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3696409.3700219
“When dealing with limited and nuanced datasets, such as the subset of the Static Facial Expression in the Wild dataset (SFEW) [5], the complexity of emotion recognition becomes more difficult to control [21].”
HCC: An Explainable Framework for Classifying Discomfort from Video
Valentine, W., Webb, M., Collum, C., Feil-Seifer, D., & Hand, E. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-77389-1_23
Text-guided Visual Prompt Tuning with Masked Images for Facial Expression Recognition
Dong, R., Yang, C., & Lam, K. (2024) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc63619.2025.10849301
“The SFEW-2 database [33] consists of over 1,500 facial images annotated with the neutral emotion and six basic emotions.”
DEER: Deep Emotion-Sets for Fine-Grained Emotion Recognition
Tahir, S. A., Mirnateghi, N., Shah, S. A. A., et al. (2024) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta63115.2024.00034
“Static Facial Emotions in the Wild (SFEW) [7] is an image-based dataset derived from the AFEW dataset that consists of video clips taken from various Hollywood movies.”
Spiking Broad Learning System for Facial Expression Recognition in the Wild
Niu, B., Ding, W., Guo, B., Wang, X., & Gong, Y. (2025) · Journal of Sensors · doi:10.1155/js/9737734
“The static facial expressions in the wild (SFEW) dataset [54] includes unrestricted facial expressions, different head postures, large age ranges, occlusion, different focal points, different facial resolutions, and real-world illumination.”
Increasing the Validity and Trustworthiness of Automated Facial Emotion Recognition Systems
Zhang, P., Yang, H., & Zhou, Z. (2025) · International Symposium on System Security, Safety, and Reliability (ISSSR) · doi:10.1109/isssr65654.2025.00059
“This approach assumes that the most frequently occurring emotion state represents the dominant effect of the subject, and it has been shown to offer robust performance in video-based affective analysis [42].”
Object Detection Modeling Using TensorFlow
Rizvi, S. W. A., Priya, R., & Misra, M. K. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-96-3256-5_26
Zou, K., Jin, L., Song, E., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5384870
Wang, C., Zhang, X., Guo, P., et al. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3599583
“3) Experiments on Public Datasets: To comprehensively evaluate its generalization capability, we conducted additional validation experiments on two standard benchmark datasets: FER (3,464 images) [53] and SFEW (1,203 images) [54], using an Ubuntu workstation equipped with RTX 3090 GPUs.”
Kim, H., Jung, Y., & Song, B. C. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3613175
“0 [45]: The SFEW dataset is constructed by selecting only static frames from the AFEW dataset [46].”
EMUSE: Emotion Based Music Recommendation System Using CNN
Jetlin, C. P., Thrayamika, R., & Swaathi, C. (2025) · International Conference on Recent Innovation in Science Engineering and Technology (ICRISET) · doi:10.1109/icriset64803.2025.11254759
“Dhall, R. Goecke, S. Lucey, and T. Gedeon [5] The authors argued that a single-modality system, like facial expression recognition, may strike a better balance between complexity and accuracy useful for real-time applications.”
Sri Yuliawati, S. (n.d.) · UNDIP Institutional Repository (UNDIP-IR) (Diponegoro University)
Saad, N. (2026) · Information systems engineering and management · doi:10.1007/978-3-032-14778-3_6
Adaptive Contrastive Learning for Semisupervised Facial Expression Recognition
Sun, B., Liao, M., Shutao Li, A., Ma, F., & Wu, Z. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3659948
Li, B., Peng, C., Zou, K., et al. (2025) · IEEE International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai67447.2025.11412830
“A key element of the VMamba model, the VSS is designed based on early state space models [19], maintaining the receptive field’s potential while ensuring linear complexity.”
FED-Bench: A Cross-Granular Benchmark for Disentangled Evaluation of Facial Expression Editing
Xue, F., Wu, X., Sun, H., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36984-0_16
A walk through randomness for face analysis in unconstrained environments
Dapogny, A. (2016) · theses.fr (ABES) · doi:10.70675/4074fb08z6ff5z472fz8eb5z34ae3e6b8a15
Crenn, A. (2019) · theses.fr (ABES) · doi:10.70675/2dfe83c3zc81dz4608zb101z6eb99c0f85d9
“Avec l’arrivée des méthodes basées sur des réseaux de neurones profonds, des nouvelles bases de données ont commencé à émerger, les bases de données dîtes "sauvages" (in the wild) [38, 36, 35].”
Construction non supervisée d'un modèle expressif spécifique à la personne
Weber, R. (2017) · theses.fr (ABES) · doi:10.70675/2f458edfz3d99z43cezb849zdf8729c5aad0
Apprentissage neuronal profond pour l'analyse de contenus multimodaux et temporels
Vielzeuf, V. (2019) · theses.fr (ABES) · doi:10.70675/cd4ec871zb372z492fz94bfz25086c5fda4a
“) [80], ce qui implique l’utilisation de nouvelles approches, permettant notamment de construire des représentations plus robustes des émotions.”
BackgroundInfluentialReconnaissance d'états émotionnels par analyse visuelle du visage et apprentissage machine
Lekdioui, K. (2018) · doi:10.70675/3aa8385cz803fz4142zb84ez9ba03c695fb3
“85 3.15 Configurations optimales de notre méthode pour atteindre les meilleurs résultats (voir Tables 3.13 et 3.14) sur l’ensemble de données CK+. . . . . . 85 3.16 Le nombre d’images où un visage est détecté, pour chaque expression dans SFEW. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8…”
BackgroundInfluentialCornec, K. L. (2020) · theses.fr (ABES) · doi:10.70675/208af321z8d3bz4b62z99f6z0b296efd57bc
Deep Learning and Information Geometry for Time-Series Classification
Brooks, D. (2020) · theses.fr (ABES) · doi:10.70675/2b220f61zf311z4863z9080z151c1780bb87
Real-Time Infant Emotion Recognition Using EfficientNet-B0 with Explainable Deep Learning
Singh, S. K., Pandey, H., Bharti, P., Yadav, P. K., Tripathi, K., & Gashroo, O. B. (2026) · IEEE International Conference on AI Engineering and Innovations (AIEI) · doi:10.1109/aiei69164.2026.11497176
“However, infant emotion recognition is a very difficult challenge and not as easy to identify as it may sound because of various reasons, such as subtlety of facial expressions; rapid changes of expression; and the significant variation (inter-subject variation) among the individual infants[14].”
Hameed, R. (2025) · Journal of Artificial Intelligence Machine Learning and Neural Network · doi:10.55529/jaimlnn.52.128.137
Chatterjee, D. (2026) · Journal of Artificial Intelligence Machine Learning and Neural Network · doi:10.55529/jaimlnn.61.64.74
Exploring Basic Expression Representation for Compound Facial Expression Recognition
Dong, R., Yang, C., Zhang, C., Xiao, J., & Lam, K. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3699031
“Most research [3], [12], [13], [14] has concentrated on the iden-tification of basic facial expressions and neutral states, utilizing well-established facial expression databases [15], [16], [17], [18], [19].”
A Comprehensive Review on Deep Learning Based Facial Emotion Recognition System
Kumar, R., Singh, S., Chauhan, R., et al. (2026) · doi:10.1109/icsscna68616.2026.11546995
“The combination of all this technique that enables computers to take better understanding of human feelings yields some impact in real life [14].”
EmoCoT: An Agentic Framework for Instance-Level Emotion Understanding
Chen, Y., & Sun, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3504-9_49
Facial Emotion Recognition using Action Units-based Machine Learning
Valdez, M. A. F., Ghergulescu, I., & Moldovan, A.-N. (2026) · Cognitive Models and Artificial Intelligence Conference (AICCONF) · doi:10.1109/aicconf69182.2026.11600666
“Four datasets were selected for this study: CK+ [11], FER2013 and its enhanced FER+ variant [30], SFEW [31] and ExpW [32].”
LDR-Net: Landmark-Guided Diverse Regional Representation Learning for Facial Expression Recognition
Lu, Y., Chang, F., Liu, C., Liu, H., & Huang, Y. (2026) · Biomimetics · doi:10.3390/biomimetics11070503
“SFEW [39] is a static facial expression dataset.”
Wang, K., Ding, R., Wang, H., et al. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3713438
“Specifically, five basic expression datasets (including three in-the-lab datasets (CK + [53], MMI [54], and Oulu-CASIA [55]) and two in-the-wild datasets (RAF-DB [56] and SFEW [57])) are employed for model training.”
Chen, X., Zou, X., Yan, Y., Gao, X., & Wang, H. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02971-4
“To ensure the diversity of basic expressions, we use five basic expression datasets to construct the training set, including three in-the-lab datasets (CK+ (Lucey et al., 2010), MMI (Pantic et al., 2005), and Oulu-CASIA (Zhao et al., 2011)), as well as two in-the-wild datasets (RAF-DB (Li et al., 2017) and SFEW (Dhall…”
InfluentialTao, R., Jiang, C.-S., & Zhang, Y.-P. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01176-6
“For SFEW and RAF-DB, the official training and test partitions were used.”
InfluentialЯнь, М., Пак, В. Г., Го, Ч., et al. (2026) · Современные наукоемкие технологии (Modern High Technologies) · doi:10.17513/snt.40933
Stability-aware distribution-adaptive learning for semi-supervised facial expression recognition
Wang, Q., Wang, N., & Zhao, J. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05756-x
“The exacerbated scarcity of reliable labels, coupled with the pervasive semantic ambiguity of human affect [9, 33],renders traditional threshold-based heuristics suboptimal for capturing ambiguous facial expressions (Fig.”
Metadata
- Authors
- Dhall, A., Goecke, R., Lucey, S., & Gedeon, T.
- Affiliations
- Australian National University (AU)
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Venue
- 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)
- Publisher
- IEEE
- Published
- 2011-11
- Pages
- 2106-2112
- ISSN
- 2473-9936 (ISSN-L)
- OpenAlex
- W2083021723
- Cited by
- 541
- References
- 32
- Citations by year
- 2026: 22 · 2025: 44 · 2024: 61 · 2023: 68 · 2022: 61 · 2021: 60 · 2020: 59 · 2019: 41 · 2018: 35 · 2017: 26 · 2016: 28 · 2015: 16 · 2014: 8 · 2013: 11 · 2012: 1
- FWCI
- 10.17
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Computer Vision Workshops (publishedVersion)
- University of Canberra Research Portal (submittedVersion)
- ANU Open Research (Australian National University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Keywords
- facial expression recognition, static facial expressions, benchmark, JAFFE
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
