CoChat
Cited by 186

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.

Former-DFER: Dynamic Facial Expression Recognition Transformer

Zhao, Zengqun, Liu, Qingshan · 2021 · Proceedings of the 29th ACM International Conference on Multimedia

Abstract

This paper proposes a dynamic facial expression recognition transformer (Former-DFER) for the in-the-wild scenario. Specifically, the proposed Former-DFER mainly consists of a convolutional spatial transformer (CS-Former) and a temporal transformer (T-Former). The CS-Former consists of five convolution blocks and N spatial encoders, which is designed to guide the network to learn occlusion and pose-robust facial features from the spatial perspective. And the temporal transformer consists of M temporal encoders, which is designed to allow the network to learn contextual facial features from the temporal perspective. The heatmaps of the leaned facial features demonstrate that the proposed Former-DFER is capable of handling the issues such as occlusion, non-frontal pose, and head motion. And the visualization of the feature distribution shows that the proposed method can learn more discriminative facial features. Moreover, our Former-DFER also achieves state-of-the-art results on the DFEW and AFEW benchmarks.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3474085.3475292

Cites

22 of 22 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 22 references

Research works printed but not linked: 57

  1. Masih Aminbeidokhti Marco Pedersoli Patrick Cardinal and Eric Granger. 2019. Emotion recognition with spatial attention and temporal softmax pooling. In ICIAR. 323--331. Masih Aminbeidokhti Marco Pedersoli Patrick Cardinal and Eric Granger. 2019. Emotion recognition with spatial attention and temporal softmax pooling. In ICIAR. 323--331. · DOI
  2. 10.1007/s10639-019-10004-6 · DOI
  3. Ba Jimmy Lei, 2016, Jamie Ryan Kiros, and Geoffrey E Hinton
  4. Wissam J Baddar and Yong Man Ro. 2019. Mode variational lstm robust to unseen modes of variation: Application to facial expression recognition. In AAAI. 3215--3223. Wissam J Baddar and Yong Man Ro. 2019. Mode variational lstm robust to unseen modes of variation: Application to facial expression recognition. In AAAI. 3215--3223. · DOI
  5. Cai Jie, 2019, Zhiyuan Li, James O'Reilly, Shizhong Han, Ping Liu, Min Chen, and Yan Tong.
  6. Joyati Chattopadhyay Souvik Kundu Arpita Chakraborty and Jyoti Sekhar Banerjee. 2018. Facial expression recognition for human computer interaction. In ICCVBIC. 1181--1192. Joyati Chattopadhyay Souvik Kundu Arpita Chakraborty and Jyoti Sekhar Banerjee. 2018. Facial expression recognition for human computer interaction. In ICCVBIC. 1181--1192. · DOI
  7. 10.1145/2663204.2666277 · DOI
  8. 10.1109/TAFFC.2016.2593719 · DOI · Paper page
  9. Darwin Charles, The expression of the emotions in man and animals
  10. 10.1145/3340555.3355710 · DOI
  11. 10.1109/MMUL.2012.26 · DOI · Paper page
  12. 10.1145/2818346.2830596 · DOI · Paper page
  13. 10.1145/3242969.3264978 · DOI
  14. 10.1145/2993148.2997632 · DOI · Paper page
  15. Rohit Girdhar Joao Carreira Carl Doersch and Andrew Zisserman. 2019. Video action transformer network. In CVPR. 244--253. Rohit Girdhar Joao Carreira Carl Doersch and Andrew Zisserman. 2019. Video action transformer network. In CVPR. 244--253. · DOI
  16. Kensho Hara Hirokatsu Kataoka and Yutaka Satoh. 2018. Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet?. In CVPR. 6546--6555. Kensho Hara Hirokatsu Kataoka and Yutaka Satoh. 2018. Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet?. In CVPR. 6546--6555. · DOI · Paper page
  17. Hu Qiaoping, 2020, RFAU: A Database for Facial Action Unit Analysis in Real Classrooms
  18. 10.1145/2663204.2666278 · DOI
  19. 10.1145/3394171.3413620 · DOI · Paper page
  20. 10.1109/TIP.2021.3051462 · DOI · Paper page
  21. Khan Salman, 2021, Fahad Shahbaz Khan, and Mubarak Shah.
  22. Jean Kossaifi Antoine Toisoul Adrian Bulat Yannis Panagakis Timothy M Hospedales and Maja Pantic. 2020. Factorized higher-order CNNs with an application to spatio-temporal emotion estimation. In CVPR. 6060--6069. Jean Kossaifi Antoine Toisoul Adrian Bulat Yannis Panagakis Timothy M Hospedales and Maja Pantic. 2020. Factorized higher-order CNNs with an application to spatio-temporal emotion estimation. In CVPR. 6060--6069. · DOI
  23. Felix Kuhnke Lars Rumberg and Jörn Ostermann. 2020. Two-Stream Aural- Visual Affect Analysis in the Wild. In FG. 366--371. Felix Kuhnke Lars Rumberg and Jörn Ostermann. 2020. Two-Stream Aural- Visual Affect Analysis in the Wild. In FG. 366--371. · DOI
  24. Vikas Kumar Shivansh Rao and Li Yu. 2020. Noisy Student Training using Body Language Dataset Improves Facial Expression Recognition. In ECCV. 756--773. Vikas Kumar Shivansh Rao and Li Yu. 2020. Noisy Student Training using Body Language Dataset Improves Facial Expression Recognition. In ECCV. 756--773. · DOI
  25. 10.1109/TIP.2020.2996086 · DOI
  26. Lee Min Kyu, 2019, Dae Ha Kim, and Byung Cheol Song.
  27. Li Shan, 2020, Deep facial expression recognition: A survey
  28. 10.1145/3340555.3355719 · DOI
  29. Liu Yang, 2021, Graph-based Facial Affect Analysis: A Review of Methods, Applications and Challenges. arXiv preprint arXiv:2103.15599 · arXiv
  30. 10.1145/3242969.3264992 · DOI
  31. Debin Meng Xiaojiang Peng Kai Wang and Yu Qiao. 2019. Frame attention networks for facial expression recognition in videos. In ICIP. 3866--3870. Debin Meng Xiaojiang Peng Kai Wang and Yu Qiao. 2019. Frame attention networks for facial expression recognition in videos. In ICIP. 3866--3870. · DOI · Paper page
  32. Trisha Mittal Uttaran Bhattacharya Rohan Chandra Aniket Bera and Dinesh Manocha. 2020. M3er: Multiplicative multimodal emotion recognition using facial textual and speech cues. In AAAI. 1359--1367. Trisha Mittal Uttaran Bhattacharya Rohan Chandra Aniket Bera and Dinesh Manocha. 2020. M3er: Multiplicative multimodal emotion recognition using facial textual and speech cues. In AAAI. 1359--1367. · DOI · Paper page
  33. 10.1109/TAFFC.2017.2713783 · DOI · Paper page
  34. 10.1145/3136755.3143012 · DOI
  35. Park Jongchan, 2018, BAM: Bottleneck Attention Module. In BMCV.
  36. 10.5555/3454287.3455008 · doi:10.5555/3454287.3455008
  37. Zhaofan Qiu Ting Yao and Tao Mei. 2017. Learning spatio-temporal representation with pseudo-3d residual networks. In ICCV. 5533--5541. Zhaofan Qiu Ting Yao and Tao Mei. 2017. Learning spatio-temporal representation with pseudo-3d residual networks. In ICCV. 5533--5541.
  38. Simonyan Karen, 2014, Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 · arXiv
  39. Sun Chen, 2019, Carl Vondrick, Kevin Murphy, and Cordelia Schmid.
  40. Touvron Hugo, 2020, Training data-efficient image transformers & distillation through attention. arXiv preprint arXiv:2012.12877 · arXiv
  41. der Maaten Laurens Van, 2008, Visualizing data using t-SNE, JMLR, 9, 2579
  42. 10.5555/3295222.3295349 · doi:10.5555/3295222.3295349
  43. 10.1145/3136755.3143011 · DOI · Paper page
  44. 10.1109/TAFFC.2020.3007531 · DOI
  45. 10.1145/3340555.3355720 · DOI
  46. 10.1109/CVPR.2013.439 · DOI
  47. Torsten Wilhelm. 2019. Towards facial expression analysis in a driver assistance system. In FG. 1--4. Torsten Wilhelm. 2019. Towards facial expression analysis in a driver assistance system. In FG. 1--4. · DOI
  48. Fuzhi Yang Huan Yang Jianlong Fu Hongtao Lu and Baining Guo. 2020. Learning texture transformer network for image super-resolution. In CVPR. 5791--5800. Fuzhi Yang Huan Yang Jianlong Fu Hongtao Lu and Baining Guo. 2020. Learning texture transformer network for image super-resolution. In CVPR. 5791--5800. · DOI · Paper page
  49. Peng Yang Qingshan Liu Xinyi Cui and Dimitris N Metaxas. 2008. Facial expression recognition using encoded dynamic features. In CVPR. 1--8. Peng Yang Qingshan Liu Xinyi Cui and Dimitris N Metaxas. 2008. Facial expression recognition using encoded dynamic features. In CVPR. 1--8. · DOI
  50. 10.1016/j.patrec.2008.03.014 · DOI
  51. Stefanos Zafeiriou Dimitrios Kollias Mihalis A Nicolaou Athanasios Papaioannou Guoying Zhao and Irene Kotsia. 2017. Aff-Wild: valence and arousal 'in-the-wild' challenge. In CVPRW. 34--41. Stefanos Zafeiriou Dimitrios Kollias Mihalis A Nicolaou Athanasios Papaioannou Guoying Zhao and Irene Kotsia. 2017. Aff-Wild: valence and arousal 'in-the-wild' challenge. In CVPRW. 34--41. · DOI · Paper page
  52. Yuan-Hang Zhang Rulin Huang Jiabei Zeng and Shiguang Shan. 2020. M3F: Multi-Modal Continuous Valence-Arousal Estimation in the Wild. In FG. 617--621. Yuan-Hang Zhang Rulin Huang Jiabei Zeng and Shiguang Shan. 2020. M3F: Multi-Modal Continuous Valence-Arousal Estimation in the Wild. In FG. 617--621. · DOI
  53. 10.1016/j.imavis.2011.07.002 · DOI · Paper page
  54. 10.1109/TIP.2021.3093397 · DOI · Paper page
  55. Zhao Zengqun, 2021, Robust Lightweight Facial Expression Recognition Network with Label Distribution Training, AAAI, 35, 3510, 10.1609/aaai.v35i4.16465 · DOI · Paper page
  56. 10.1109/TPAMI.2013.173 · DOI
  57. 10.1109/CVPR.2011.5995345 · DOI · Paper page

Cited by

See all 186

Metadata

Authors
Zhao, Z., & Liu, Q.
Venue
Proceedings of the 29th ACM International Conference on Multimedia
Publisher
ACM
Published
2021-10-17
Pages
1553-1561
OpenAlex
W3206349670
Cited by
186
References
22
FWCI
8.32
Type
conference paper
Language
en
Open access
closed
Funders
  • National Natural ScienceFoundation of China (61825601)
  • Natural Science Foundation of Jiangsu Province (BK20192004B)

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Former-DFER: Dynamic Facial Expression Recognition Transformer. https://app.cochat.ai/papers/10.1145/3474085.3475292
The paper
Zhao, Z., & Liu, Q. (2021). Former-DFER: Dynamic Facial Expression Recognition Transformer. Proceedings of the 29th ACM International Conference on Multimedia. https://doi.org/10.1145/3474085.3475292

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.