The DOI matches its Crossref record; 61 of the 72 references it cites were found in a registry or an index.
ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challenges
Open accessAbstract
This paper describes the third Affective Behavior Analysis in-the-wild (ABAW) Competition, held in conjunction with IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2022. The 3rd ABAW Competition is a continuation of the Competitions held at ICCV 2021, IEEE FG 2020 and IEEE CVPR 2017 Conferences, and aims at automatically analyzing affect. This year the Competition encompasses four Challenges: i) uni-task Valence-Arousal Estimation, ii) uni-task Expression Classification, iii) uni-task Action Unit Detection, and iv) MultiTask-Learning. All the Challenges are based on a common benchmark database, Aff-Wild2, which is a large scale in-the-wild database and the first one to be annotated in terms of valence-arousal, expressions and action units. In this paper, we present the four Challenges, with the utilized Competition corpora, we outline the evaluation metrics and present both the baseline systems and the top performing teams’ per Challenge. Finally we illustrate the obtained results of the baseline systems and of all participating teams. More information regarding the Competition and the leaderboard for each Challenge can be found in the competition’s website: http://ibug.doc.ic.ac.uk/resources/cvpr-2022-3rd-abaw.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“we use the Aff-Wild2 dataset (Kollias and Zafeiriou, 2019; Kollias, 2022), which contains 548 video clips collected from YouTube in realworld environments. Each clip has several frames of aligned faces and each frame is annotated with a facial expression. It has eight classes of emotions (six basic emotions, neutral , and other ).”
From A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations (2023) · cites this paper as Kollias, 2022
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild
Deng, J., Guo, J., Ververas, E., Kotsia, I., & Zafeiriou, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00525 · Cited by 1,681
The Expression Of The Emotions In Man And Animals
Darwin, C. D. (1998) · doi:10.1093/oso/9780195112719.001.0001 · Cited by 733
Evidence of convergent validity on the dimensions of affect
Russell, J. A. (1978) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.36.10.1152 · Cited by 495
Facial Action Coding System (FACS)
Ekman, P. (2002) · Medical Entomology and Zoology · Cited by 433
Deep Affect Prediction in-the-Wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond
Kollias, D., Tzirakis, P., Nicolaou, M. A., Papaioannou, A., Zhao, G., Schuller, B. W., Kotsia, I., & Zafeiriou, S. P. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01158-4 · Cited by 406
Self-citationAff-Wild: Valence and Arousal ‘In-the-Wild’ Challenge
Zafeiriou, S. P., Kollias, D., Nicolaou, M. A., Papaioannou, A., Zhao, G., & Kotsia, I. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.248 · Cited by 297
Self-citationAnalysing Affective Behavior in the First ABAW 2020 Competition
Kollias, D., Schulc, A., Hajiyev, E., & Zafeiriou, S. P. (2020) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg47880.2020.00126 · Cited by 238
Self-citationFace Behavior a la carte: Expressions, Affect and Action Units in a Single NetworkPreprint
Kollias, D., Sharmanska, V., & Zafeiriou, S. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11111 · Cited by 228
Self-citationExpression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace
Kollias, D., & Zafeiriou, S. (2019) · arXiv · doi:10.48550/arxiv.1910.04855 · Cited by 210
Self-citationAnalysing Affective Behavior in the second ABAW2 Competition
Kollias, D., & Zafeiriou, S. P. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00408 · Cited by 168
Self-citationMultimodal Multi-task Learning for Dimensional and Continuous Emotion Recognition
Chen, S., Jin, Q., Zhao, J., & Wang, S. (2017) · Proceedings of the 7th Annual Workshop on Audio/Visual Emotion Challenge · doi:10.1145/3133944.3133949 · Cited by 147
Aff-Wild2: Extending the Aff-Wild Database for Affect RecognitionPreprint
Kollias, D., & Zafeiriou, S. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.07770 · Cited by 142
Self-citationRecognition of Affect in the Wild Using Deep Neural Networks
Kollias, D., Nicolaou, M. A., Kotsia, I., Zhao, G., & Zafeiriou, S. P. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.247 · Cited by 123
Self-citationA Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
Praveen, R. G., de Melo, W. C., Ullah, N., Aslam, M. H., Zeeshan, O., Denorme, T., Pedersoli, M., Koerich, A. L., Bacon, S., Cardinal, P., et al. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00278 · Cited by 115
Transformer-based Multimodal Information Fusion for Facial Expression Analysis
Zhang, W., Qiu, F., Wang, S., Zeng, H., Zhang, Z., An, R., Ma, B., & Ding, Y. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00271 · Cited by 114
Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face StudyPreprint
Kollias, D., Sharmanska, V., & Zafeiriou, S. P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03790 · Cited by 110
Self-citationAffect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified FrameworkPreprint
Kollias, D., & Zafeiriou, S. P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.15792 · Cited by 107
Self-citationIncremental Boosting Convolutional Neural Network for Facial Action Unit RecognitionPreprint
Han, S., Meng, Z., Khan, A.-S., & Tong, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.05395 · Cited by 97
Multitask Emotion Recognition with Incomplete Labels
Deng, D., Chen, Z., & Shi, B. E. (2020) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg47880.2020.00131 · Cited by 94
Chang, W.-Y., Hsu, S.-H., & Chien, J.-H. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.246 · Cited by 81
Two-Stream Aural-Visual Affect Analysis in the Wild
Kuhnke, F., Rumberg, L., & Östermann, J. (2020) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg47880.2020.00056 · Cited by 73
A Multi-Task Learning & Generation Framework: Valence-Arousal, Action Units & Primary ExpressionsPreprint
Kollias, D., & Zafeiriou, S. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.07771 · Cited by 50
Self-citationCoarse-to-Fine Cascaded Networks with Smooth Predicting for Video Facial Expression Recognition
Xue, F., Tan, Z., Zhu, Y. M., Ma, Z., & Guo, G. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00269 · Cited by 46
Multitask Multi-database Emotion Recognition
Vu, M. T., Beurton‐Aimar, M., & Marchand, S. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00406 · Cited by 38
A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysis
Wang, L., Wang, S., Qi, J., & Suzuki, K. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00402 · Cited by 36
Antoniadis, P., Pikoulis, I., Filntisis, P. P., & Maragos, P. A. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00407 · Cited by 31
Zhang, S., An, R., Ding, Y., & Guan, C. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00265 · Cited by 30
Time-Continuous Audiovisual Fusion with Recurrence vs Attention for In-The-Wild Affect Recognition
Karas, V., Tellamekala, M. K., Mallol-Ragolta, A., Valstar, M., & Schuller, B. W. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00266 · Cited by 27
Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 CompetitionPreprint
Zhang, W., Guo, Z., Chen, K., Li, L., Zhang, Z., & Ding, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03708 · Cited by 23
Facial Expression Recognition with Swin TransformerPreprint
Kim, J.-H., Kim, N., & Won, C. S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13472 · Cited by 22
Frame-level Prediction of Facial Expressions, Valence, Arousal and Action Units for Mobile DevicesPreprint
Savchenko, A. V. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13436 · Cited by 22
Affective Expression Analysis in-the-wild using Multi-Task Temporal Statistical Deep Learning Model
Do, N.-T., Nguyen-Quynh, T.-T., & Kim, S.-H. (2020) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg47880.2020.00093 · Cited by 21
A Multi-modal and Multi-task Learning Method for Action Unit and Expression RecognitionPreprint
Jin, Y., Zheng, T., Gao, C., & Xu, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.04187 · Cited by 21
Causal affect prediction model using a past facial image sequence
Oh, G., Jeong, E., & Lim, S. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00395 · Cited by 17
Multi-label Transformer for Action Unit DetectionPreprint
Tallec, G., Yvinec, E., Dapogny, A., & Bailly, K. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.12531 · Cited by 17
Gera, D., & Balasubramanian, S. (2021) · International Journal of Engineering Trends and Technology · doi:10.14445/22315381/ijett-v69i7p231 · Cited by 14
Multi-modal Emotion Estimation for in-the-wild VideosPreprint
Meng, L., Liu, Y., Liu, X., Huang, Z., Cheng, Y., Wang, M., Liu, C., & Jin, Q. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13032 · Cited by 14
An Audio-Video Deep and Transfer Learning Framework for Multimodal Emotion Recognition in the wildPreprint
Dresvyanskiy, D., Рюмина, Е. В., Kaya, H., Markitantov, M., Karpov, A. A., & Minker, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03692 · Cited by 13
An Ensemble Approach for Facial Expression Analysis in VideoPreprint
Nguyen, H.-H., Huynh, V. T., & Kim, S.-H. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.12891 · Cited by 12
Multi-modal Multi-label Facial Action Unit Detection with TransformerPreprint
Wang, L., Wang, S., & Qi, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13301 · Cited by 10
Multi-Label Class Balancing Algorithm for Action Unit DetectionPreprint
Pahl, J., Rieger, I., & Seuß, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.03238 · Cited by 9
$M^3$T: Multi-Modal Continuous Valence-Arousal Estimation in the WildPreprint
Zhang, Y., Huang, R., Zeng, J., Shan, S., & Chen, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.02957 · Cited by 9
Facial Action Unit Recognition With Multi-models EnsemblingPreprint
Jiang, W., Wu, Y., Qiao, F., Meng, L., Deng, Y., & Liu, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13046 · Cited by 8
Facial Expression Recognition based on Multi-head Cross Attention NetworkPreprint
Jeong, J.-Y., Hong, Y.-G., Kim, D., Jung, Y., & Jeong, J.-W. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13235 · Cited by 8
Gera, D., & Balasubramanian, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.14440 · Cited by 7
FAU, Facial Expressions, Valence and Arousal: A Multi-task SolutionPreprint
Deng, D., Chen, Z., & Shi, B. E. (2020) · arXiv (Cornell University) · Cited by 7
Spatial and Temporal Networks for Facial Expression Recognition in the Wild VideosPreprint
Mao, S., Fan, X., & Peng, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.05160 · Cited by 6
Emotion Recognition for In-the-wild VideosPreprint
Liu, H., Zeng, J., Shan, S., & Chen, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.05447 · Cited by 6
Technical Report for Valence-Arousal Estimation on Affwild2 DatasetPreprint
Li, I.-H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.01502 · Cited by 5
Technical Report for Valence-Arousal Estimation in ABAW2 ChallengePreprint
Xie, H.-X., Li, I.-H., Lo, L., Shuai, H.-H., & Cheng, W.-H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03891 · Cited by 5
Multi-label Relation Modeling in Facial Action Units DetectionPreprint
Ji, X., Ding, Y., Li, L., Chen, Y., & Fan, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.01105 · Cited by 5
A Multi-term and Multi-task Analyzing Framework for Affective Analysis in-the-wildPreprint
Youoku, S., Toyoda, Y., Yamamoto, T., Saito, J., Kawamura, R., Mi, X., & Murase, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.13885 · Cited by 5
Deng, D., Wu, L., & Shi, B. E. (2021) · arXiv (Cornell University) · Cited by 5
Multi-model Ensemble Learning Method for Human Expression RecognitionPreprint
Yu, J., Cai, Z., He, P., Xie, G., & Ling, Q. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.14466 · Cited by 5
Action Units Recognition Using Improved Pairwise Deep ArchitecturePreprint
Saito, J., Mi, X., Uchida, A., Youoku, S., Yamamoto, T., Murase, K., & Nakayama, O. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03143 · Cited by 5
Multiple Emotion Descriptors Estimation at the ABAW3 ChallengePreprint
Deng, D. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.12845 · Cited by 4
Audio-visual Attentive Fusion for Continuous Emotion Recognition.Preprint
Zhang, S., Ding, Y., Wei, Z., & Guan, C. (2021) · arXiv (Cornell University) · Cited by 3
An Attention-based Method for Action Unit Detection at the 3rd ABAW CompetitionPreprint
Hoai, D. L., Lim, E., Choi, E., Kim, S., Pant, S., Lee, G.-S., Kim, S.-H., & Yang, H.-J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.12428 · Cited by 2
Facial Action Unit Recognition Based on Transfer LearningPreprint
Wang, S., Chang, Y., & Wang, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.14694 · Cited by 2
Multitask Emotion Recognition Model with Knowledge Distillation and Task DiscriminatorPreprint
Jeong, E., Oh, G., & Lim, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13072 · Cited by 2
Flagged first, then by citations
11 of the 72 references couldn’t be matched to a known paper.
Research works printed but not linked: 4
- whissel, 1989, The dictionary of affect in language, emotion: Theory, research and experience: vol. 4, the measurement of emotions
- frijda, 1986, The Emotions
- goodfellow, 2016, Deep Learning
- cowie, 2000, ’feel-trace’: An instrument for recording perceived emotion in real time, ISCA Tutorial and Research Workshop (ITRW) on Speech and Emotion
Cited by
Sorted by citations
Advances in Facial Expression Recognition: A Survey of Methods, Benchmarks, Models, and Datasets
Kopalidis, T., Solachidis, V., Vretos, N., & Daras, P. (2024) · Information · doi:10.3390/info15030135 · Cited by 205
A Review of Key Technologies for Emotion Analysis Using Multimodal Information
Zhu, X., Guo, C., Feng, H., Huang, Y., Feng, Y., Wang, X., & Wang, R. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10287-z · Cited by 143
A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
Praveen, R. G., de Melo, W. C., Ullah, N., Aslam, M. H., Zeeshan, O., Denorme, T., Pedersoli, M., Koerich, A. L., Bacon, S., Cardinal, P., et al. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00278 · Cited by 115
Transformer-based Multimodal Information Fusion for Facial Expression Analysis
Zhang, W., Qiu, F., Wang, S., Zeng, H., Zhang, Z., An, R., Ma, B., & Ding, Y. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00271 · Cited by 114
Kollias, D., Tzirakis, P., Baird, A., Cowen, A., & Zafeiriou, S. P. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00626 · Cited by 102
Self-citation
Metadata
- Authors
- Kollias, D.
- Affiliations
- Queen Mary University of London (GB)
- Corresponding author
- Kollias, Dimitrios
- ORCID
- Kollias, Dimitrios
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 2327-2335
- OpenAlex
- W4292794012
- Cited by
- 147
- References
- 72
- Citations by year
- 2026: 6 · 2025: 41 · 2024: 33 · 2023: 47 · 2022: 20
- FWCI
- 46.11
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Queen Mary Research Online (Queen Mary University of London) (submittedVersion)
- arXiv (Cornell University)
- 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 › Human Pose and Action Recognition
- Keywords
- valence-arousal estimation, facial expression recognition, action unit detection, multi-task learning, Aff-Wild2, ABAW challenge, benchmark database
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
