Ying Tai(邰颖)

I am a Researcher and Team Lead at Tencent Youtu Lab, where I work on computer vision and machine learning.

I got my Ph.D. degree from the Department of Computer Science and Engineering, Nanjing University of Science & Technology (NUST) in 2017, and my advisor is Prof. Jian Yang. In 2016, I spent 6 wonderful months as a visiting student at Prof. Xiaoming Liu's lab in Michigan State University.

Most of my works have released codes in [TencentYoutuResearch], with over 4.0K stars and 750 forks.

Email  /  Google Scholar  /  Github  /  LinkedIn

profile photo

Recent news

  • 12/2021 – 3 papers accepted by AAAI'22, with the acceptance rate to be 15%

  • 09/2021 – 2 papers on blind SR and ViT accepted by NeurIPS'21, with the acceptance rate to be 26%

  • 07/2021 – 2 papers on crowd counting accepted by ICCV'21 (1 Oral and 1 Poster), with the acceptance rate to be 25.9%

  • 07/2021 – Our ASFD on face detection is accepted by ACM MM'21

  • 04/2021 – 4 papers accepted by IJCAI'21, with the acceptance rate to be 13.9%

  • 04/2021 – Our Team Imagination is the winner of CVPR NTIRE 2021 Challenge on Video Spatial-Temporal Super-Resolution

  • 03/2021 – 3 papers accepted by CVPR'21 (1 Oral and 2 Posters), with the acceptance rate to be 23.7%

  • 12/2020 – 4 papers accepted by AAAI'21, with the acceptance rate to be 21%

  • 09/2020 – Training codes of RealSR are available in Tencent official github account [Tencent-RealSR].

  • 07/2020 – 6 papers accepted by ECCV'20, with the acceptance rate to be 27%

  • 05/2020 – Our RealSR model (Team name: Impressionism) won both tracks of CVPR NTIRE 2020 Challenge on Real-World Super-Resolution

  • 02/2020 – 3 papers accepted by CVPR'20, with the acceptance rate to be 22.1%

  • 11/2019 – 2 papers (Action Proposal & Action Recognition) accepted by AAAI'20, with the acceptance rate to be 20.6%. The code of our DBG is released at [ActionDetection-DBG], which achieves Top 1 performance on ActivityNet Challenge 2019 on Temporal Action Proposals

  • 02/2019 – Our DSFD on face detection is accepted by CVPR'19, with the acceptance rate to be 25.2%

  • 11/2018 – 2 papers (face alignement & adaptive metric learning) accepted by AAAI'19, with the acceptance rate to be ONLY 16.2%

  • 10/2018 – We released a novel Dual Shot Face Detector (DSFD) framework that achieves Top 1 performance on all FIVE settings of WIDER FACE (Easy/Medium/Hard) and FDDB (Discrete/Continuous) datasets

  • 07/2018 – 1 paper accepted by ECCV'18

  • 02/2018 – 1 paper accepted by CVPR'18 (SPOTLIGHT Presentation)

  • 07/2017 – 1 paper accepted by ICCV'17 (SPOTLIGHT Presentation)

  • 03/2017 – 1 paper accepted by CVPR'17


Preprints (* equal contribution, # corresponding author)

Collaborative Learning for Faster StyleGAN Embedding
S. Guan, Y. Tai, B. Ni, F. Zhu, F. Huang and X. Yang.
arXiv, 2020
arXiv

Aurora Guard: Reliable Face Anti-Spoofing via Mobile Lighting System
J. Zhang, Y. Tai, T. Yao, J. Meng, S. Ding, C. Wang, J. Li, F. Huang and R. Ji.
arXiv, 2021
arXiv

Publications (* equal contribution, # corresponding author)

Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution
G. Tao, X. Ji, W. Wang, S. Chen, C. Lin, Y. Cao, T. Lu, D. Luo, Y. Tai
Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021
Paper (Coming soon)

A novel framework S2K that predicts the kernel from spectrum in frequency domain

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model
J. Zhang, C. Xu, J. Li, W. Chen, Y. Wang, Y. Tai, S. Chen, C. Wang, F. Huang and R. Liu.
Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021
arXiv

An interesting viewpoint between EA and Transfomer, and propose an EA based Transformer framework for both NLP and CV tasks

Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework
Q. Song*, C. Wang*, Z. Jiang, Y. Wang, Y. Tai, C. Wang, J. Li, F. Huang and Y. Wu.
International Conference on Computer Vision (ICCV), 2021 [Oral]
arXiv / Code (Coming soon) GitHub stars

We propose a novel simple and elegant framework for crowd counting, which directly predicts the crowd location instead of using density map estimation adopted in most previous methods.

Uniformity in Heterogeneity: Diving Deep into Count Interval Partition for Crowd Counting
C. Wang*, Q. Song*, B. Zhang, Y. Wang, Y. Tai, X. Hu, C. Wang, J. Li, J. Ma, and Y. Wu..
International Conference on Computer Vision (ICCV), 2021
arXiv / Code (Coming soon) GitHub stars
ASFD: Automatic and Scalable Face Detector
J. Li*, B. Zhang*, Y. Wang, Y. Tai, Z. Zhang, C. Wang, J. Li, X. Huang and Y. Xia.
ACM International Conference on Multimedia (ACM MM), 2021
arXiv

Ranked No. 1 on WIDER FACE

HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
Y. Wang*, X. Chen*, J. Zhu, W. Chu, Y. Tai#, C. Wang, J. Li, Y. Wu, F. Huang and R. Ji.
International Joint Conference on Artificial Intelligence (IJCAI), 2021
arXiv / Project / Poster / Video (1min)

Context-Aware Image Inpainting with Learned Semantic Priors
W. Zhang, J. Zhu, Y. Tai, Y. Wang, W. Chu, B. Ni, C. Wang and X. Yang.
International Joint Conference on Artificial Intelligence (IJCAI), 2021
arXiv / Code (Official) GitHub stars

Dual Reweighting Domain Generalization for Face Presentation Attack Detection
S. Liu, K. Zhang, T. Yao, K. Sheng, S. Ding, Y. Tai, J. Li, Y. Xie and L. Ma.
International Joint Conference on Artificial Intelligence (IJCAI), 2021
arXiv

SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking
J. Peng*, Z. Jiang*, Y. Gu*, Y. Wu, Y. Wang, Y. Tai, C. Wang and W. Lin.
International Joint Conference on Artificial Intelligence (IJCAI), 2021
arXiv

Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection
Z. Zhang, Y. Ge, R. Chen, Y. Tai, Y. Yan, J. Yang, C. Wang, J. Li, and F. Huang.
Computer Vision and Pattern Recognition (CVPR), 2021 [Oral]
Paper / Code (Official) GitHub stars

Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
C. Lin*, C. Xu*, D. Luo, Y. Wang, Y. Tai, C. Wang, J. Li, F. Huang and Y. Fu.
Computer Vision and Pattern Recognition (CVPR), 2021
arXiv / Paper / Code (Official) GitHub stars

Learning to Restore Hazy Video: A New Real-World Dataset and A New Method
X. Zhang*, H. Dong*, J. Pan, C. Zhu, Y. Tai, C. Wang, J. Li, F. Huang and F. Wang.
Computer Vision and Pattern Recognition (CVPR), 2021
Paper
Frequency Consistent Adaptation for Real World Super Resolution
X. Ji*, G. Tao*, Y. Cao, Y. Tai, T. Lu, C. Wang, J. Li, and F. Huang.
AAAI Conference on Artificial Intelligence (AAAI), 2021
arXiv

Improved version of our prior work RealSR

Learning Comprehensive Motion Representation for Action Recognition
M. Wu*, B. Jiang*, D. Luo, J. Yan, Y. Wang, Y. Tai, C. Wang, J. Li, F. Huang, and X. Yang.
AAAI Conference on Artificial Intelligence (AAAI), 2021
arXiv / Code (Official) GitHub stars

Extented version of our prior works TEINet and TDRL

Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing
Z. Chen, T. Yao, K. Sheng, S. Ding, Y. Tai, J. Li, F. Huang, and X. Jin.
AAAI Conference on Artificial Intelligence (AAAI), 2021
arXiv

To Choose or to Fuse? Scale Selection for Crowd Counting
Q. Song*, C. Wang*, Y. Wang, Y. Tai, C. Wang, J. Li, J. Wu, and J. Ma.
AAAI Conference on Artificial Intelligence (AAAI), 2021
Paper / Code (Official) GitHub stars

FAN: Feature Adaptation Network for Surveillance Face Recognition and Normalization
X. Yin, Y. Tai, Y. Huang and X. Liu.
Asian Conference on Computer Vision (ACCV), 2020
Paper

Novel framework to improve surveillance face recognition & normalization from unpaired data

Improving Face Recognition from Hard Samples via Distribution Distillation Loss
Y. Huang*, P. Shen*, Y. Tai#, S. Li#, X. Liu, J. Li, F. Huang, and R. Ji.
European Conference on Computer Vision (ECCV), 2020
arXiv / Paper (Official) / Code (Official) GitHub stars

SSCGAN: Facial Attribute Editing via Style Skip Connections
W. Chu, Y. Tai#, C. Wang, J. Li, F. Huang, and R. Ji.
European Conference on Computer Vision (ECCV), 2020
Paper (Official)

Face Anti-Spoofing via Disentangled Representation Learning
K. Zhang, T. Yao, J. Zhang, Y. Tai#, S. Ding, J. Li, F. Huang, H. Song and L. Ma.
European Conference on Computer Vision (ECCV), 2020
Paper (Official)

Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End
Joint Multiple-Object Detection and Tracking

J. Peng, C. Wang, F. Wan, Y. Wu, Y. Wang, Y. Tai, C. Wang, J. Li, F. Huang and Y. Fu.
European Conference on Computer Vision (ECCV), 2020 [Spotlight]
arXiv / Paper (Official) / Code (Official) GitHub stars

Temporal Distinct Representation Learning for 2D-CNN-based Action Recognition
J. Weng, D. Luo, Y. Wang, Y. Tai, C. Wang, J. Li, F. Huang, X. Jiang and J. Yuan.
European Conference on Computer Vision (ECCV), 2020
Paper (Official)

Adversarial Semantic Data Augmentation for Human Pose Estimation
Y. Bin, X. Cao, X. Chen, Y. Ge, Y. Tai, C. Wang, J. Li, F. Huang, C. Gao and N. Sang.
European Conference on Computer Vision (ECCV), 2020
arXiv / Paper (Official) / Code (Official) GitHub stars

State-of-the-art performance on MPII and LSP

Real-World Super-Resolution via Kernel Estimation and Noise Injection
X. Ji, Y. Cao, Y. Tai#, C. Wang, J. Li, and F. Huang.
Computer Vision and Pattern Recognition Workshop (CVPRW), 2020
Paper / Code (Tencent) GitHub stars / Code (Personal) GitHub stars / Code (NCNN-vulkan) GitHub stars / OpenBenchmarking.org / Challenge Report

Winner of CVPR NTIRE 2020 Challenge on Real-World Super-Resolution

CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
Y. Huang, Y. Wang, Y. Tai#, X. Liu, P. Shen, S. Li#, J. Li, and F. Huang.
Computer Vision and Pattern Recognition (CVPR), 2020
Paper (Official) / Code GitHub stars

Learning by Analogy: Reliable Supervision from Transformations for
Unsupervised Optical Flow Estimation

L. Liu, J. Zhang, Y. Liu, Y. Wang, Y. Tai, D. Luo, C. Wang, J. Li, and F. Huang.
Computer Vision and Pattern Recognition (CVPR), 2020
Paper (Official) / Code GitHub stars

Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
Y. Yan, J. Qin, J. Chen, L. Liu, F. Zhu, Y. Tai, and L. Shao.
Computer Vision and Pattern Recognition (CVPR), 2020
Paper (Official) / Code GitHub stars

Fast Learning of Temporal Action Proposal via Dense Boundary Generator
C. Lin*, J. Li*, Y. Wang, Y. Tai, D. Luo, Z. Cui, C. Wang, J. Li, F. Huang and R. Ji.
AAAI Conference on Artificial Intelligence (AAAI), 2020
arXiv / Code GitHub stars

Ranked No. 1 on ActivityNet Challenge 2019 on Temporal Action Proposals

TEINet: Towards an Efficient Architecture for Video Recognition
Z. Liu*, D. Luo*, Y. Wang, L. Wang, Y. Tai, C. Wang, J. Li, F. Huang and T. Lu.
AAAI Conference on Artificial Intelligence (AAAI), 2020
arXiv

DSFD: Dual Shot Face Detector
J. Li, Y. Wang, C. Wang, Y. Tai, J. Qian, J. Yang, C.e Wang, J. Li and F. Huang.
Computer Vision and Pattern Recognition (CVPR), 2019
arXiv / Paper (Official) / Code GitHub stars

Ranked No. 1 on WIDER FACE and FDDB (Until 2019.01)

Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos
Y. Tai*, Y. Liang*, X. Liu, L. Duan, J. Li, C. Wang, F. Huang and Y. Chen.
AAAI Conference on Artificial Intelligence (AAAI), 2019
arXiv / Paper (Official) / Supp / Code GitHub stars

Data-Adaptive Metric Learning with Scale Alignment
S. Chen, C. Gong, J. Yang, Y. Tai, L. Hui and J. Li.
AAAI Conference on Artificial Intelligence (AAAI), 2019
Paper (Official)

Person Search via A Mask-Guided Two-Stream CNN Model
D. Chen, S. Zhang, W. Ouyang, J. Yang and Y. Tai.
European Conference on Computer Vision (ECCV), 2018
Paper / Poster

FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
Y. Tai*, Y. Chen*, X. Liu, C. Shen, J. Yang.
Computer Vision and Pattern Recognition (CVPR), 2018 [Spotlight]
Paper (Official) / arXiv / Code GitHub stars / Demo / Slides / Poster

MemNet: A Persistent Memory Network for Image Restoration
Y. Tai, J. Yang, X. Liu, C. Xu.
International Conference on Computer Vision (ICCV), 2017 [Spotlight]
Paper / Code GitHub stars / Poster

Image Super-Resolution via Deep Recursive Residual Network
Y. Tai, J. Yang, X. Liu.
Computer Vision and Pattern Recognition (CVPR), 2017
Paper / Code GitHub stars / Project / Poster

My first paper that has over 1,000 google scholar citations

Nuclear Norm based Matrix Regression with Applications to Face Recognition with Occlusion and Illumination Changes
J. Yang, L. Luo, J. Qian, Y. Tai, F. Zhang and Y. Xu.
IEEE Trans. on Pattern Analysis and Machine Intelligence, 2017
Paper

Structural Orthogonal Procrustes Regression for Face Recognition with Pose Variations and Misalignment
Y. Tai, J. Yang, F. Zhang, Y. Zhang, L. Luo, J. Qian.
SIAM Conference on Data Mining (SDM), 2016 [Oral]
Paper

Face Recognition with Pose Variations and Misalignment via Orthogonal Procrustes Regression
Y. Tai, J. Yang, Y. Zhang, L. Luo, J. Qian and Y. Chen
IEEE Trans. on Image Processing, 2016
Paper

Learning Discriminative Singular Value Decomposition Representation for Face Recognition
Y. Tai, J. Yang, L. Luo, F. Zhang and J. Qian
Pattern Recognition, 2016
Paper

Awards

  • 2021 Winner of CVPR NTIRE 2021 Challenge on Video Super-Resolution: Spatial-Temporal (Team name: Imagination)

  • 2020 Winner of CVPR NTIRE 2020 Challenge on Real-World Super-Resolution (Team name: Impressionism)

  • 2018 Stars of Youtu Lab, Tencent

  • 2018, 2019, 2020 Outstanding Staff Award, Tencent

  • 2018 Excellent Doctoral Dissertation of Nanjing University of Science and Technology, China

  • ICCV'17 Student Volunteer Travel Award

  • 2017 Outstanding Graduate

  • 2016 National Graduate Scholarship


Professional activities

  • Reviewer for CVPR'(17, 18, 19, 20, 21), ICCV'(17,19), ECCV'(18, 20), AAAI'(19, 20), ICLR'20, NIPS'20

  • Reviewer for Trans. on Pattern Analysis and Machine Intelligence (TPAMI), International Journal of Computer Vision (IJCV), IEEE Trans. on Image Processing (TIP), Pattern Recognition, Pattern Recognition Letters


  • Last modified in Apr. 2021. For the style of my personal website, Please refer to the wonderful page from Jon Barron.