DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild
The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Recently, facial expression recognition (FER) in the wild has gained a lot of researchers' attention because it is a valuable topic to enable the FER techniques to move from the laboratory to the real applications. In this paper, we focus on this challenging but interesting topic and make contributions from three aspects. First, we present a new large-scale 'in-the-wild' dynamic facial expression database, DFEW (Dynamic Facial Expression in the Wild), consisting of over 16,000 video clips from thousands of movies. These video clips contain various challenging interferences in practical scenarios such as extreme illumination, occlusions, and capricious pose changes. Second, we propose a novel method called Expression-Clustered Spatiotemporal Feature Learning (EC-STFL) framework to deal with dynamic FER in the wild. Third, we conduct extensive benchmark experiments on DFEW using a lot of spatiotemporal deep feature learning methods as well as our proposed EC-STFL. Experimental results show that DFEW is a well-designed and challenging database, and the proposed EC-STFL can promisingly improve the performance of existing spatiotemporal deep neural networks in coping with the problem of dynamic FER in the wild. Our DFEW database is publicly available and can be freely downloaded from https://dfew-dataset.github.io/.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Learning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593
Measuring nominal scale agreement among many raters.
Fleiss, J. L. (1971) · Psychological Bulletin · doi:10.1037/h0031619 · Cited by 8,733 · cited 1×
“In this section, we discuss the quality of emotion annotation based on Fleiss’s Kappa test [10].”
MethodLarge-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 1×
“The action databases include UCF101 [36], Sports 1M [16], Kinect 700 [2], and Moments In Time [29].”
Constants across cultures in the face and emotion.
Ekman, P., & Friesen, W. V. (1971) · Journal of Personality and Social Psychology · doi:10.1037/h0030377 · Cited by 5,509 · cited 1×
“Ekman believes that the seven basic emotions are universal and independent of the cultural mismatch [6], culture mismatch indeed exists and worth considering because the labeling bias can be removed as far as possible.”
BackgroundUcf101: A dataset of 101 human actions classes from videos in the wild
Soomro, K., Zamir, A. R., & Shah, M. (2012) · arXiv · doi:10.48550/arxiv.1212.0402 · Cited by 4,575
A Discriminative Feature Learning Approach for Deep Face Recognition
Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_31 · Cited by 4,077 · cited 1×
“We set trade-off coefficient λ of models with EC-STFL to 10, and trade-off coefficient of center loss to 1 × 10−4 according to [40].”
MethodA Closer Look at Spatiotemporal Convolutions for Action Recognition
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2017) · arXiv · doi:10.48550/arxiv.1711.11248 · Cited by 3,664 · cited 2×
“, C3D [37], I3DRGB [2], R3D18 [38], 3D Resnet18 [12], P3D [32], and two CNNRNN models, i.”
AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild
Mollahosseini, A., Hasani, B., & Mahoor, M. H. (2019) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2017.2740923 · Cited by 2,338
Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
Hara, K., Kataoka, H., & Satoh, Y. (2017) · 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw.2017.373 · Cited by 726 · cited 3×
“In this paper, we conduct five 3D CNN models, i.e., C3D [37], I3D-RGB [2], R3D18 [38], 3D Resnet18 [12], P3D [32], and two CNN-RNN models, i.e., VGG11+LSTM and Resnet18+LSTM for benchmarks.”
BackgroundMethodInfluentialVideo-based emotion recognition using CNN-RNN and C3D hybrid networks
Fan, Y., Lu, X., Li, D., & Liu, Y. (2016) · Proceedings of the 18th ACM International Conference on Multimodal Interaction · doi:10.1145/2993148.2997632 · Cited by 556
Learning Expressionlets on Spatio-temporal Manifold for Dynamic Facial Expression Recognition
Liu, M., Shan, S., Wang, R., & Chen, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.226 · Cited by 392 · cited 1×
“Over the past decades, researchers have proposed a lot of wellperforming methods for recognizing facial expressions, and these methods achieved promising performance in the lab-controlled environments [8, 24, 30, 41–43].”
BackgroundA Short Note on the Kinetics-700-2020 Human Action Dataset
Smaira, L., Carreira, J., Noland, E., Clancy, E., Wu, A., & Zisserman, A. (2020) · arXiv · doi:10.48550/arxiv.2010.10864 · Cited by 334
Context-Aware Emotion Recognition Networks
Lee, J., Kim, S., Kim, S., Park, J., & Sohn, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01024 · Cited by 323 · cited 4×
“Following this method, several dynamic facial expression databases, e.g., Aff-Wild [17], AFEW [4, 5], and CAER [19] have been successively built and released over the past few years, which indeed advances the research of dynamic FER in the wild.”
BackgroundMethodInfluentialAFEW-VA database for valence and arousal estimation in-the-wild
Kossaifi, J., Tzimiropoulos, G., Todorovic, S., & Pantic, M. (2017) · Image and Vision Computing · doi:10.1016/j.imavis.2017.02.001 · Cited by 236 · cited 2×
“Aff-Wild [17] 298 Web Valence-arousal 8 Yes AFEW 7.0 [4] 1,809 54 Movies 7 basic expressions 2 Yes AFEW-VA [18] 600 AFEW database Valence-arousal 2 Yes CAER [19] 13,201 79 TVshows 7 basic expressions 3 Yes DFEW 16,372 1500 movies 7 basic expressions 10 Yes ed their focus to a challenging but…”
BackgroundInfluentialLearning supervised scoring ensemble for emotion recognition in the wild
Hu, P., Cai, D., Wang, S., Yao, A., & Chen, Y. (2017) · Proceedings of the 19th ACM International Conference on Multimodal Interaction · doi:10.1145/3136755.3143009 · Cited by 162
Cited by
Chumachenko, K., Iosifidis, A., & Gabbouj, M. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00470 · Cited by 34
Xie, H. (2025) · Proceedings of the 2025 International Conference on Artificial Intelligence and Educational Systems · doi:10.1145/3744367.3744415
Metadata
- Authors
- Jiang, X., Zong, Y., Zheng, W., Tang, C., Xia, W., Lu, C., & Liu, J.
- Venue
- Proceedings of the 28th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2020-10-12
- Pages
- 2881-2889
- OpenAlex
- W3093370878
- Cited by
- 207
- References
- 17
- FWCI
- 12.79
- Type
- conference paper
- Language
- en
- Open access
- closed
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.