Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Jiayi Wang

Jiayi Wang

Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation

Jul 18, 2022
Hegui Zhu, Zhan Gao, Jiayi Wang, Yange Zhou, Chengqing Li

Figure 1 for Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation

Figure 2 for Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation

Figure 3 for Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation

Figure 4 for Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation

* 12 pages, 9 figures

Access Paper or Ask Questions

Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity

Apr 19, 2022
Nanqing Dong, Jiayi Wang, Irina Voiculescu

Figure 1 for Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity

Figure 2 for Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity

Figure 3 for Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity

Figure 4 for Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity

* Accepted by CVPR 2022 Workshop on Learning with Limited Labelled Data for Image and Video Understanding

Access Paper or Ask Questions

Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model

Mar 19, 2022
Jiayi Wang, Rongzhou Bao, Zhuosheng Zhang, Hai Zhao

Figure 1 for Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model

Figure 2 for Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model

Figure 3 for Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model

Figure 4 for Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model

* Accepted by findings of ACL 2022

Access Paper or Ask Questions

QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task

Dec 30, 2021
Jiayi Wang, Ke Wang, Boxing Chen, Yu Zhao, Weihua Luo, Yuqi Zhang

Figure 1 for QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task

Figure 2 for QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task

Figure 3 for QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task

Figure 4 for QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task

* Winner of WMT 2021 QE shared task 1

Access Paper or Ask Questions

Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

Sep 15, 2021
Ke Wang, Yangbin Shi, Jiayi Wang, Yuqi Zhang, Yu Zhao, Xiaolin Zheng

Figure 1 for Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

Figure 2 for Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

Figure 3 for Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

Figure 4 for Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

* Accepted by Findings of EMNLP 2021

Access Paper or Ask Questions

Projected State-action Balancing Weights for Offline Reinforcement Learning

Sep 10, 2021
Jiayi Wang, Zhengling Qi, Raymond K. W. Wong

Figure 1 for Projected State-action Balancing Weights for Offline Reinforcement Learning

Figure 2 for Projected State-action Balancing Weights for Offline Reinforcement Learning

Access Paper or Ask Questions

RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video

Jun 22, 2021
Jiayi Wang, Franziska Mueller, Florian Bernard, Suzanne Sorli, Oleksandr Sotnychenko, Neng Qian, Miguel A. Otaduy, Dan Casas, Christian Theobalt

Figure 1 for RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video

Figure 2 for RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video

Figure 3 for RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video

Figure 4 for RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video

* ACM Transactions on Graphics (TOG) 39 (6), 1-16, 2020
* SIGGRAPH Asia 2020

Access Paper or Ask Questions

Matrix Completion with Model-free Weighting

Jun 09, 2021
Jiayi Wang, Raymond K. W. Wong, Xiaojun Mao, Kwun Chuen Gary Chan

Figure 1 for Matrix Completion with Model-free Weighting

Figure 2 for Matrix Completion with Model-free Weighting

* Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021

Access Paper or Ask Questions

Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

May 30, 2021
Rongzhou Bao, Jiayi Wang, Hai Zhao

Figure 1 for Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

Figure 2 for Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

Figure 3 for Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

Figure 4 for Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

* Findings of ACL: ACL 2021

Access Paper or Ask Questions

Enhancing Pre-trained Language Model with Lexical Simplification

Dec 30, 2020
Rongzhou Bao, Jiayi Wang, Zhuosheng Zhang, Hai Zhao

Figure 1 for Enhancing Pre-trained Language Model with Lexical Simplification

Figure 2 for Enhancing Pre-trained Language Model with Lexical Simplification

Figure 3 for Enhancing Pre-trained Language Model with Lexical Simplification

Figure 4 for Enhancing Pre-trained Language Model with Lexical Simplification

Access Paper or Ask Questions