Yapeng Tian

PhD Candidate

Department of Computer Science
University of Rochester, NY

Email: yapengtian@rochester.edu

[Google Scholar][CV] [Github] [DBLP]  

Short Bio

I am a Fifth-year PhD Candidate in the URCS.  I received my M.E. degree from Tsinghua University in 2017, and B.E. degree from Xidian University in 2013.

My research interests center around solving core computer vision and audition problems and applying the developed learning approaches to broad AI applications in multisensory perception, computational photography, AR/VR, and HCI.

I'm on the job market this year. Please reach out if you think I’d be a good fit for your academic department.


News

  • 12/2021: Two papers are accepted by AAAI 2022.
  • 10/2021: One paper on sounding object localization is accepted by BMVC 2021!
  • 07/2021: One paper on video matting is accepted by ICCV 2021!
  • 03/2021: Our two works: co-learn sounding object visual grounding and sound separation and audio-visual robustness under attacks are accepted by CVPR 2021!
  • 02/2021: We will co-organize a CVPR 2021 Tutorial on Audio-visual Scene Understanding!
  • 01/2021: Co-organized the WACV 2021 Tutorial on Audio-visual Scene Understanding. More details can be found in our website.
  • 10/2020: I was in the top 10% of high-scoring reviewers for NeurIPS 2020!
  • 07/2020: Our audio-visual video parsing work got accepted by ECCV 2020 as a Spotlight.
  • 05/2020: Our three papers on deep audio prior, sounding object visual grounding and sound separation, and audio-visual video parsing will be presented in the CVPR 2020 Sight and Sound workshop.
  • 02/2020: Two papers on video restoration got accepted by CVPR 2020! Congratulations to all co-authors!
  • 01/2020: RDN is accepted by IEEE TPAMI! Congratulations to Yulun!
  • 12/2019: Please check our deep audio prior paper.
  • 08/2019: One paper is accepted by IEEE TIP. Congratulations to Xuechen!
  • 07/2019: One paper is accepted by ICCV 2019. Congratulations to Wei!
  • 05/2019: Our two works: audio-visual event localization and audio-visual video captioning will be presented in the CVPR 2019 Sight and Sound workshop.
  • 02/2019: I will serve as an ICCV 2019 reviewer.
  • 12/2018: Two papers are posted on ArXiv. Please watch the corresponding demos.
  • 07/2018: One paper is accepted by ECCV 2018! AVE dataset and codes have been released.
  • 02/2018: One paper is accepted by CVPR 2018. Congratulations to Yulun!
  • 07/2017: I recieve 'Outstanding Graduate of Tsinghua university' and 'Outstanding Master Thesis Award'.
  • 03/2017: I will join Prof. Chenliang Xu's lab to pursue a PhD degree at University of Rochester!

Publications

Vision and Sound

Space-Time Memory Network for Sounding Object Localization in Videos

Sizhe Li*, Yapeng Tian*, and Chenliang Xu
BMVC, 2021. [Paper][Code]
Can audio-visual integration strengthen robustness under multimodal attacks?

Yapeng Tian and Chenliang Xu
CVPR, 2021. [Paper][Code]
Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation

Yapeng Tian, Di Hu, and Chenliang Xu
CVPR, 2021. [Paper][Code]
Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing

Yapeng Tian, Dingzeyu Li, and Chenliang Xu
CVPR Sight and Sound Workshop, 2020. [Short Paper] [Demo]
ECCV, 2020. [Paper][Code and Datset] (Spotlight)
Deep Audio Prior

Yapeng Tian, Chenliang Xu, and Dingzeyu Li
CVPR Sight and Sound Workshop, 2020. [Paper] [Code][Demo]
Interpretable and Controllable Audio-Visual Video Captioning

Yapeng Tian, Chenxiao Guan, Goodman Justin, Marc Moore, and Chenliang Xu
CVPR Sight and Sound Workshop, 2019. [Early version] [Workshop Paper] [Website]
Audio-Visual Event Localization in Unconstrained Videos

Yapeng Tian, Jing Shi, Bochen Li, Zhiyao Duan, and Chenliang Xu
CVPR Sight and Sound Workshop, 2019. (Oral)
ECCV,  2018.[PDF] [Project] [Code]

Video Restoration

Video Matting via Consistency-Regularized Graph Neural Networks

Tiantian Wang, Sifei Liu, Yapeng Tian, Kai Li, and Ming-Hsuan Yang
ICCV, 2021. [Paper]
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution

Xiaoyu Xiang*, Yapeng Tian*, Yulun Zhang, Yun Fu, Jan Allebach+, and Chenliang Xu+
CVPR, 2020. [Paper] [Code] [Demo ] (Equal contribution*;Equal advising+)
TDAN: Temporally Deformable Alignment Network for Video Super-Resolution

Yapeng Tian, Yulun Zhang, Yun Fu, and Chenliang Xu
CVPR, 2020. [Paper] [ArXiv 2018 Version] [Code] [Demo]

Image Restoration

Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution

Bin Xia, Yapeng Tian, Yucheng Hang, Wenming Yang, Qingmin Liao, Jie Zhou
AAAI, 2022. [Paper][Code]
Efficient Non-Local Contrastive Attention for Image Super-Resolution

Bin Xia*, Yucheng Hang*, Yapeng Tian, Wenming Yang, Qingmin Liao, Jie Zhou
AAAI, 2022. [Paper][Code]
Residual Dense Network for Image Restoration

Yulun Zhang, Yapeng Tian, Yu Kong , Bineng Zhong, Yun Fu
IEEE TPAMI, 2020. [Paper][Code]
CFSNet: Toward a Controllable Feature Space for Image Restoration

Wei Wang, Ruiming Guo, Yapeng Tian, and Wenming Yang
ICCV, 2019. [Paper] [Code]
LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution

Wenming Yang, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue, Qingmin Liao
IEEE Trans. Image Processing (TIP), 2019. [Paper]
Deep Learning for Single Image Super-Resolution: A Brief Review

Wenming Yang, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue, Qingmin Liao
IEEE Trans. Multimedia (TMM), 2019. [Paper]
Residual Dense Network for Image Super-Resolution

Yulun Zhang, Yapeng Tian, Yu Kong , Bineng Zhong, Yun Fu
CVPR,  2018. [PDF]  [Code] (Spotlight)
NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results

Radu Timofte, Eirikur Agustsson, Luc Van Gool, ..., Xintao Wang, Yapeng Tian, Ke Yu, Yulun Zhang, Shixiang Wu, Chao Dong, Liang Lin, Yu Qiao, ...
CVPR Workshops,  2017. [PDF] 
Consistent Coding Scheme for Single-Image Super-Resolution Via Independent Dictionaries

Wenming Yang, Yapeng Tian, Fei Zhou*, Qingmin Liao, Hai Chen and Chenglin Zheng
IEEE Trans. Multimedia (TMM),  2016. [PDF][Project] 
Anchored Neighborhood Regression based Single Image Super-Resolution from Self-examples

Yapeng Tian, Fei Zhou, Wenming Yang*, Xuesen Shang and Qingmin Liao
ICIP 2016, [PDF] [Project] [Code]
Single-Image Super-Resolution Using Clustering-Based Global Regression and Propagation Filtering

Wenming Yang,Yapeng Tian, Fei Zhou, Tingrong Yuan, Xuesen Shang and Qingmin Liao
ACPR 2015, [PDF] (Oral)

 

Awards

 

Professional Activities