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

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Xiang Li

Xiang Li

PVTv2: Improved Baselines with Pyramid Vision Transformer


Jul 17, 2021
Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao

Figure 1 for PVTv2: Improved Baselines with Pyramid Vision Transformer
Figure 2 for PVTv2: Improved Baselines with Pyramid Vision Transformer
Figure 3 for PVTv2: Improved Baselines with Pyramid Vision Transformer
Figure 4 for PVTv2: Improved Baselines with Pyramid Vision Transformer
* Technical Report 
  Access Paper or Ask Questions

Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes


Jul 07, 2021
Xiang Li, Lingjing Wang, Yi Fang

* 14 pages 
  Access Paper or Ask Questions

A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning


Jul 03, 2021
Wenchao Zhang, Chong Fu, Xiangshi Chang, Tengfei Zhao, Xiang Li, Chiu-Wing Sham

Figure 1 for A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning
Figure 2 for A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning
Figure 3 for A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning
Figure 4 for A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning

  Access Paper or Ask Questions

Adaptive Control for Robotic Manipulation of Deformable Linear Objects with Offline and Online Learning of Unknown Models


Jul 01, 2021
Mingrui Yu, Hanzhong Zhong, Fangxun Zhong, Xiang Li

Figure 1 for Adaptive Control for Robotic Manipulation of Deformable Linear Objects with Offline and Online Learning of Unknown Models
Figure 2 for Adaptive Control for Robotic Manipulation of Deformable Linear Objects with Offline and Online Learning of Unknown Models
Figure 3 for Adaptive Control for Robotic Manipulation of Deformable Linear Objects with Offline and Online Learning of Unknown Models
Figure 4 for Adaptive Control for Robotic Manipulation of Deformable Linear Objects with Offline and Online Learning of Unknown Models

  Access Paper or Ask Questions

Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding


Jun 20, 2021
Chaolei Tan, Zihang Lin, Jian-Fang Hu, Xiang Li, Wei-Shi Zheng

Figure 1 for Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding
Figure 2 for Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding
Figure 3 for Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding
Figure 4 for Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding
* A technical report on our solution for Person in Context(PIC) Challenge HCVG track at CVPR 2021 workshop 
  Access Paper or Ask Questions

The Image Local Autoregressive Transformer


Jun 04, 2021
Chenjie Cao, Yuxin Hong, Xiang Li, Chengrong Wang, Chengming Xu, XiangYang Xue, Yanwei Fu

Figure 1 for The Image Local Autoregressive Transformer
Figure 2 for The Image Local Autoregressive Transformer
Figure 3 for The Image Local Autoregressive Transformer
Figure 4 for The Image Local Autoregressive Transformer

  Access Paper or Ask Questions

Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning


May 31, 2021
Binbin Xie, Jinsong Su, Yubin Ge, Xiang Li, Jianwei Cui, Junfeng Yao, Bin Wang

Figure 1 for Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning
Figure 2 for Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning
Figure 3 for Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning
Figure 4 for Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning

  Access Paper or Ask Questions

Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation


May 30, 2021
Zhiyong Wu, Lingpeng Kong, Wei Bi, Xiang Li, Ben Kao

Figure 1 for Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation
Figure 2 for Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation
Figure 3 for Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation
Figure 4 for Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation
* To appear at ACL 2021 main conference 
  Access Paper or Ask Questions

An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks


May 19, 2021
Cong Xu, Xiang Li, Min Yang

Figure 1 for An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks
Figure 2 for An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks
Figure 3 for An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks
Figure 4 for An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks
* 15 pages 
  Access Paper or Ask Questions

PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text


May 09, 2021
Wenhai Wang, Enze Xie, Xiang Li, Xuebo Liu, Ding Liang, Zhibo Yang, Tong Lu, Chunhua Shen

Figure 1 for PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
Figure 2 for PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
Figure 3 for PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
Figure 4 for PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
* Accepted to TPAMI 2021 
  Access Paper or Ask Questions

Challenges and Outlook in Robotic Manipulation of Deformable Objects


May 04, 2021
Jihong Zhu, Andrea Cherubini, Claire Dune, David Navarro-Alarcon, Farshid Alambeigi, Dmitry Berenson, Fanny Ficuciello, Kensuke Harada, Xiang Li, Jia Pan, Wenzhen Yuan

Figure 1 for Challenges and Outlook in Robotic Manipulation of Deformable Objects
Figure 2 for Challenges and Outlook in Robotic Manipulation of Deformable Objects
Figure 3 for Challenges and Outlook in Robotic Manipulation of Deformable Objects
Figure 4 for Challenges and Outlook in Robotic Manipulation of Deformable Objects

  Access Paper or Ask Questions

Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood


Apr 12, 2021
Cong Li, Min Shi, Bo Qu, Xiang Li

Figure 1 for Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood
Figure 2 for Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood
Figure 3 for Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood
Figure 4 for Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood

  Access Paper or Ask Questions

Towards Multi-Scale Style Control for Expressive Speech Synthesis


Apr 08, 2021
Xiang Li, Changhe Song, Jingbei Li, Zhiyong Wu, Jia Jia, Helen Meng

Figure 1 for Towards Multi-Scale Style Control for Expressive Speech Synthesis
Figure 2 for Towards Multi-Scale Style Control for Expressive Speech Synthesis
Figure 3 for Towards Multi-Scale Style Control for Expressive Speech Synthesis
Figure 4 for Towards Multi-Scale Style Control for Expressive Speech Synthesis
* 5 pages, 4 figures, submitted to INTERSPEECH 2021 
  Access Paper or Ask Questions

Development and Validation of a Deep Learning Model for Prediction of Severe Outcomes in Suspected COVID-19 Infection


Mar 29, 2021
Varun Buch, Aoxiao Zhong, Xiang Li, Marcio Aloisio Bezerra Cavalcanti Rockenbach, Dufan Wu, Hui Ren, Jiahui Guan, Andrew Liteplo, Sayon Dutta, Ittai Dayan, Quanzheng Li

Figure 1 for Development and Validation of a Deep Learning Model for Prediction of Severe Outcomes in Suspected COVID-19 Infection
Figure 2 for Development and Validation of a Deep Learning Model for Prediction of Severe Outcomes in Suspected COVID-19 Infection
Figure 3 for Development and Validation of a Deep Learning Model for Prediction of Severe Outcomes in Suspected COVID-19 Infection
Figure 4 for Development and Validation of a Deep Learning Model for Prediction of Severe Outcomes in Suspected COVID-19 Infection
* Varun Buch, Aoxiao Zhong and Xiang Li contribute equally to this work 
  Access Paper or Ask Questions

Structure-Enhanced Meta-Learning For Few-Shot Graph Classification


Mar 11, 2021
Shunyu Jiang, Fuli Feng, Weijian Chen, Xiang Li, Xiangnan He

Figure 1 for Structure-Enhanced Meta-Learning For Few-Shot Graph Classification
Figure 2 for Structure-Enhanced Meta-Learning For Few-Shot Graph Classification
Figure 3 for Structure-Enhanced Meta-Learning For Few-Shot Graph Classification
Figure 4 for Structure-Enhanced Meta-Learning For Few-Shot Graph Classification
* Submitted to AI Open 
  Access Paper or Ask Questions

Privacy-Preserving Distributed SVD via Federated Power


Mar 01, 2021
Xiao Guo, Xiang Li, Xiangyu Chang, Shusen Wang, Zhihua Zhang

Figure 1 for Privacy-Preserving Distributed SVD via Federated Power
Figure 2 for Privacy-Preserving Distributed SVD via Federated Power
Figure 3 for Privacy-Preserving Distributed SVD via Federated Power
Figure 4 for Privacy-Preserving Distributed SVD via Federated Power

  Access Paper or Ask Questions

Bridging Unpaired Facial Photos And Sketches By Line-drawings


Feb 25, 2021
Meimei Shang, Fei Gao, Xiang Li, Jingjie Zhu, Lingna Dai

Figure 1 for Bridging Unpaired Facial Photos And Sketches By Line-drawings
Figure 2 for Bridging Unpaired Facial Photos And Sketches By Line-drawings
Figure 3 for Bridging Unpaired Facial Photos And Sketches By Line-drawings
Figure 4 for Bridging Unpaired Facial Photos And Sketches By Line-drawings
* accepted by ICASSP2021 
  Access Paper or Ask Questions

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions


Feb 24, 2021
Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao

Figure 1 for Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Figure 2 for Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Figure 3 for Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Figure 4 for Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
* 13 pages, 6 figures, technical report 
  Access Paper or Ask Questions

SceneRec: Scene-Based Graph Neural Networks for Recommender Systems


Feb 12, 2021
Gang Wang, Ziyi Guo, Xiang Li, Dawei Yin, Shuai Ma

Figure 1 for SceneRec: Scene-Based Graph Neural Networks for Recommender Systems
Figure 2 for SceneRec: Scene-Based Graph Neural Networks for Recommender Systems
Figure 3 for SceneRec: Scene-Based Graph Neural Networks for Recommender Systems
Figure 4 for SceneRec: Scene-Based Graph Neural Networks for Recommender Systems

  Access Paper or Ask Questions

Delayed Projection Techniques for Linearly Constrained Problems: Convergence Rates, Acceleration, and Applications


Jan 05, 2021
Xiang Li, Zhihua Zhang

Figure 1 for Delayed Projection Techniques for Linearly Constrained Problems: Convergence Rates, Acceleration, and Applications
Figure 2 for Delayed Projection Techniques for Linearly Constrained Problems: Convergence Rates, Acceleration, and Applications
Figure 3 for Delayed Projection Techniques for Linearly Constrained Problems: Convergence Rates, Acceleration, and Applications
Figure 4 for Delayed Projection Techniques for Linearly Constrained Problems: Convergence Rates, Acceleration, and Applications

  Access Paper or Ask Questions

Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More


Jan 01, 2021
Xiulong Yang, Hui Ye, Yang Ye, Xiang Li, Shihao Ji

Figure 1 for Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More
Figure 2 for Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More
Figure 3 for Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More
Figure 4 for Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More

  Access Paper or Ask Questions