Chao Yao(姚超)

Associated Professor, University of Science and Technology Beijing

yaochao [at] ustb.edu.cn, yaochao1986 [at] gmail.com

I’m currently a Associated Professor at School of Computer & Communication Engineering, University of Science and Technology Beijing (USTB). Before joining USTB, I obtained my Ph.D. from the Center of Digital Media Information Processing Institute of Information and Science, Beijing jiaotong Unviersity in June, 2016, supervised by Prof. Yao Zhao. In 2014/09–2015/09, I was a visitor of Prof. Pascal Frossard’s group at École Polytechnique Fédérale de Lausanne (EPFL).

Research interest: image compression, video coding, human-computer interaction and time series data analysis and prediction. Interested in internship or collaboration? Contact me.

news

Apr 17, 2024	We have 1 paper accepted to IJCAI 2024! ✨ 😄
Mar 29, 2024	We have 1 paper accepted to PR! ✨ 😄
Mar 13, 2024	We have 2 papers accepted to ICME 2024! ✨ 😄
Dec 9, 2023	We have 2 papers accepted to AAAI 2024! ✨ 😄
Sep 7, 2023	We have 1 paper accepted to IEEE TIP! ✨ 😄

selected publications

AAAI

Spatial-Related Sensors Matters: 3D Human Motion Reconstruction Assisted with Textual Semantics

Xueyuan Yang, Chao Yao, and Xiaojuan Ban

In Proceedings of the AAAI Conference on Artificial Intelligence, 2024

arXiv Bib PDF Code

@inproceedings{Yang2024AAAI,
  author = {Yang, Xueyuan and Yao, Chao and Ban, Xiaojuan},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  title = {Spatial-Related Sensors Matters: 3D Human Motion Reconstruction Assisted with Textual Semantics},
  year = {2024},
}

AAAI

Semantic-Lens: Instance-Centric Semantic Alignment for Video Super-Resolution

Qi Tang, Yao Zhao, Meiqin Liu, and 2 more authors

In Proceedings of the AAAI Conference on Artificial Intelligence, 2024

arXiv Bib PDF Code

@inproceedings{Tang2024AAAI,
  author = {Tang, Qi and Zhao, Yao and Liu, Meiqin and Jin, Jian and Yao, Chao},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  title = {Semantic-Lens: Instance-Centric Semantic Alignment for Video Super-Resolution},
  year = {2024},
}

IEEE T.IP

JNMR: Joint Non-Linear Motion Regression for Video Frame Interpolation

Meiqin Liu, Chenming Xu, Chao Yao, and 2 more authors

IEEE Transactions on Image Processing, 2023

Bib PDF Code Website

@article{liu2023JNMR,
  title = {JNMR: Joint Non-Linear Motion Regression for Video Frame Interpolation},
  author = {Liu, Meiqin and Xu, Chenming and Yao, Chao and Lin, Chunyu and Zhao, Yao},
  journal = {IEEE Transactions on Image Processing},
  volume = {32},
  number = {},
  pages = {5283--5295},
  year = {2023},
  publisher = {IEEE},
}

ACM MM

Kernel Dimension Matters: to Activate Available Kernels for Real-time Video Super-Resolution

Shuo Jin, Meiqin Liu, Chao Yao, and 2 more authors

In ACM International Conference on Multimedia(ACM MM), 2023

arXiv Bib PDF Code

@inproceedings{Jin2023ACM,
  author = {Jin, Shuo and Liu, Meiqin and Yao, Chao and Lin, Chunyu and Zhao, Yao},
  booktitle = {ACM International Conference on Multimedia(ACM MM)},
  title = {Kernel Dimension Matters: to Activate Available Kernels for Real-time Video Super-Resolution},
  year = {2023},
  publisher = {ACM},
}

IEEE T.CSVT

Temporal Consistency Learning of Inter-Frames for Video Super-Resolution

Meiqin Liu, Shuo Jin, Chao Yao, and 2 more authors

IEEE Transactions on Circuits and Systems for Video Technology, 2023

Bib PDF Code Website

@article{liu2023temporal,
  title = {Temporal Consistency Learning of Inter-Frames for Video Super-Resolution},
  author = {Liu, Meiqin and Jin, Shuo and Yao, Chao and Lin, Chunyu and Zhao, Yao},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  volume = {33},
  number = {4},
  pages = {1507--1520},
  year = {2023},
  publisher = {IEEE},
}

ECCV

Feature representation matters: End-to-end learning for reference-based image super-resolution

Yanchun Xie, Jimin Xiao, Mingjie Sun, and 2 more authors

In European Conference Computer Vision (ECCV), 2020

Bib PDF

@inproceedings{xie2020feature,
  title = {Feature representation matters: End-to-end learning for reference-based image super-resolution},
  author = {Xie, Yanchun and Xiao, Jimin and Sun, Mingjie and Yao, Chao and Huang, Kaizhu},
  booktitle = {European Conference Computer Vision (ECCV)},
  pages = {230--245},
  year = {2020},
  organization = {Springer},
}

IEEE T.BC

Video streaming adaptation strategy for multiview navigation over DASH

Chao Yao, Jimin Xiao, Yao Zhao, and 1 more author

IEEE Transactions on Broadcasting, 2019

Bib PDF

@article{yao2019video,
  title = {Video streaming adaptation strategy for multiview navigation over DASH},
  author = {Yao, Chao and Xiao, Jimin and Zhao, Yao and Ming, Anlong},
  journal = {IEEE Transactions on Broadcasting},
  volume = {65},
  number = {3},
  pages = {521--533},
  year = {2019},
  publisher = {IEEE},
}

IEEE T.MM

Depth map down-sampling and coding based on synthesized view distortion

Chao Yao, Jimin Xiao, Tammam Tillo, and 3 more authors

IEEE Transactions on Multimedia, 2016

Bib PDF

@article{yao2016depth,
  title = {Depth map down-sampling and coding based on synthesized view distortion},
  author = {Yao, Chao and Xiao, Jimin and Tillo, Tammam and Zhao, Yao and Lin, Chunyu and Bai, Huihui},
  journal = {IEEE Transactions on Multimedia},
  volume = {18},
  number = {10},
  pages = {2015--2022},
  year = {2016},
  publisher = {IEEE},
}

IEEE T.BC

Depth map driven hole filling algorithm exploiting temporal correlation information

Chao Yao, Tammam Tillo, Yao Zhao, and 3 more authors

IEEE Transactions on Broadcasting, 2014

Bib PDF

@article{yao2014depth,
  title = {Depth map driven hole filling algorithm exploiting temporal correlation information},
  author = {Yao, Chao and Tillo, Tammam and Zhao, Yao and Xiao, Jimin and Bai, Huihui and Lin, Chunyu},
  journal = {IEEE Transactions on Broadcasting},
  volume = {60},
  number = {2},
  pages = {394--404},
  year = {2014},
  publisher = {IEEE},
}