Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 212

The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.

Audio-Driven Emotional Video Portraits

Open access
Ji, Xinya, Zhou, Hang, Wang, Kaisiyuan, Wu, Wayne, Loy, Chen Change, Cao, Xun, Xu, Feng · 2021 · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

Despite previous success in generating audio-driven talking heads, most of the previous studies focus on the correlation between speech content and the mouth shape. Facial emotion, which is one of the most important features on natural human faces, is always neglected in their methods. In this work, we present Emotional Video Portraits (EVP), a system for synthesizing high-quality video portraits with vivid emotional dynamics driven by audios. Specifically, we propose the Cross-Reconstructed Emotion Disentanglement technique to decompose speech into two decoupled spaces, i.e., a duration-independent emotion space and a duration- dependent content space. With the disentangled features, dynamic 2D emotional facial landmarks can be deduced. Then we propose the Target-Adaptive Face Synthesis technique to generate the final high-quality video portraits, by bridging the gap between the deduced landmarks and the natural head poses of target videos. Extensive experiments demonstrate the effectiveness of our method both qualitatively and quantitatively.1

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.

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

Integrity signals

Registry

Crossref · 10.1109/cvpr46437.2021.01386

Cites

10 of 10 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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 10 references

Research works printed but not linked: 37

  1. wang, 2010, Synthesizing photo-real talking head via trajectory-guided sample selection, Eleventh Annual Conference of the International Speech Communication Association
  2. 10.24963/ijcai.2019/129 · DOI · Paper page
  3. pumarola, 2018, Ganimation: Anatomically-aware facial animation from a single image, Proceedings of the European Conference on Computer Vision (ECCV)
  4. 10.1016/j.eswa.2014.03.026 · DOI
  5. wang, 2020, Mead: A large-scale audio-visual dataset for emotional talking-face generation, ECCV
  6. 10.1007/s11263-019-01251-8 · DOI · Paper page
  7. 10.1007/978-3-030-58517-4_42 · DOI · Paper page
  8. suwajanakorn, 2017, Synthesizing obama: learning lip sync from audio, ACM Transactions on Graphics (TOG), 10.1145/3072959.3073640 · DOI · Paper page
  9. 10.1109/ICIP.2019.8803603 · DOI · Paper page
  10. der maaten, 2008, Visualizing data using t-sne, Journal of Machine Learning Research
  11. 10.1109/WACV45572.2020.9093527 · DOI
  12. 10.1109/HRI.2010.5453272 · DOI · Paper page
  13. 10.1145/3306346.3322999 · DOI
  14. jia, 2020, Et-gan: Crosslanguage emotion transfer based on cycle-consistent generative adversarial networks, ECAI
  15. kim, 2019, Neural style-preserving visual dubbing, ACM Transactions on Graphics (TOG), 10.1145/3355089.3356500 · DOI
  16. 10.1145/3072959.3073658 · DOI · Paper page
  17. lee, 2018, Diverse image-to-image translation via disentangled representations, Proceedings of the European Conference on Computer Vision (ECCV)
  18. kim, 2018, Deep video portraits, ACM Transactions on Graphics (TOG), 10.1145/3197517.3201283 · DOI · Paper page
  19. logan, 2000, Mel frequency cepstral coefficients for music modeling, ISMIR
  20. 10.1145/2816795.2818122 · DOI
  21. chung, 2017, You said that?, BMVC
  22. 10.1109/CVPR.2018.00917 · DOI · Paper page
  23. 10.1145/2897824.2925984 · DOI · Paper page
  24. green, 2002, Canny edge detection tutorial, Retrieved March
  25. huang, 2018, Multimodal unsupervised image-to-image translation, Proceedings of the European Conference on Computer Vision (ECCV)
  26. 10.1145/311535.311537 · DOI · Paper page
  27. berndt, 1994, Using dynamic time warping to find patterns in time series, KDD Workshop
  28. cao, 2013, Facewarehouse: A 3d facial expression database for visual computing, IEEE Transactions on Visualization and Computer Graphics
  29. chen, 2018, Lip movements generation at a glance, Proceedings of the European Conference on Computer Vision (ECCV)
  30. chen, 2020, Talking-head generation with rhythmic head motion, European Conference on Computer Vision (ECCV)
  31. zhu, 2017, Unpaired image-to-image translation using cycleconsistent adversarial networks, IEEE International Conference on Computer Vision (ICCV)
  32. 10.1109/CVPR.2019.00802 · DOI · Paper page
  33. zhou, 2021, Pose-controllable talking face generation by implicitly modularized audio-visual representation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  34. 10.24963/ijcai.2020/327 · DOI
  35. zhou, 2018, Visemenet: Audiodriven animator-centric speech animation, ACM Transactions on Graphics (TOG), 10.1145/3197517.3201292 · DOI · Paper page
  36. 10.1109/CVPR.2018.00227 · DOI · Paper page
  37. 10.1109/CVPR42600.2020.00595 · DOI

Cited by

See all 212

Metadata

Authors
Ji, X., Zhou, H., Wang, K., Wu, W., Loy, C. C., Cao, X., & Xu, F.
Venue
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2021-06
Pages
14075-14084
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3174763799
Cited by
212
References
10
FWCI
13.25
Type
conference paper
Language
en
Open access
green

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: Audio-Driven Emotional Video Portraits. https://app.cochat.ai/papers/10.1109/cvpr46437.2021.01386
The paper
Ji, X., Zhou, H., Wang, K., Wu, W., Loy, C. C., Cao, X., & Xu, F. (2021). Audio-Driven Emotional Video Portraits. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr46437.2021.01386

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.