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 Kai Zhang

Kai Zhang

An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems


Jan 10, 2022
Guangdong Xue, Qin Chang, Jian Wang, Kai Zhang, Nikhil R. Pal

Figure 1 for An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems
Figure 2 for An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems
Figure 3 for An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems
Figure 4 for An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems

  Access Paper or Ask Questions

Gendered Differences in Face Recognition Accuracy Explained by Hairstyles, Makeup, and Facial Morphology


Dec 29, 2021
Vítor Albiero, Kai Zhang, Michael C. King, Kevin W. Bowyer

Figure 1 for Gendered Differences in Face Recognition Accuracy Explained by Hairstyles, Makeup, and Facial Morphology
Figure 2 for Gendered Differences in Face Recognition Accuracy Explained by Hairstyles, Makeup, and Facial Morphology
Figure 3 for Gendered Differences in Face Recognition Accuracy Explained by Hairstyles, Makeup, and Facial Morphology
Figure 4 for Gendered Differences in Face Recognition Accuracy Explained by Hairstyles, Makeup, and Facial Morphology
* arXiv admin note: substantial text overlap with arXiv:2008.06989 
  Access Paper or Ask Questions

Sequential Recommendation with Bidirectional Chronological Augmentation of Transformer


Dec 13, 2021
Juyong Jiang, Yingtao Luo, Jae Boum Kim, Kai Zhang, Sunghun Kim

Figure 1 for Sequential Recommendation with Bidirectional Chronological Augmentation of Transformer
Figure 2 for Sequential Recommendation with Bidirectional Chronological Augmentation of Transformer
Figure 3 for Sequential Recommendation with Bidirectional Chronological Augmentation of Transformer
Figure 4 for Sequential Recommendation with Bidirectional Chronological Augmentation of Transformer

  Access Paper or Ask Questions

Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation


Dec 01, 2021
Kai Zhang, Yifan Sun, Rui Wang, Haichang Li, Xiaohui Hu

Figure 1 for Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
Figure 2 for Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
Figure 3 for Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
Figure 4 for Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
* 13 pages, 2 figures, submitted to BMVC2021 
  Access Paper or Ask Questions

Scalable Causal Structure Learning: New Opportunities in Biomedicine


Oct 15, 2021
Pulakesh Upadhyaya, Kai Zhang, Can Li, Xiaoqian Jiang, Yejin Kim

Figure 1 for Scalable Causal Structure Learning: New Opportunities in Biomedicine
Figure 2 for Scalable Causal Structure Learning: New Opportunities in Biomedicine
Figure 3 for Scalable Causal Structure Learning: New Opportunities in Biomedicine
Figure 4 for Scalable Causal Structure Learning: New Opportunities in Biomedicine

  Access Paper or Ask Questions

Towards Flexible Blind JPEG Artifacts Removal


Sep 29, 2021
Jiaxi Jiang, Kai Zhang, Radu Timofte

Figure 1 for Towards Flexible Blind JPEG Artifacts Removal
Figure 2 for Towards Flexible Blind JPEG Artifacts Removal
Figure 3 for Towards Flexible Blind JPEG Artifacts Removal
Figure 4 for Towards Flexible Blind JPEG Artifacts Removal
* Accepted by ICCV 2021, Code: https://github.com/jiaxi-jiang/FBCNN 
  Access Paper or Ask Questions

GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks


Sep 13, 2021
Weicheng Ma, Renze Lou, Kai Zhang, Lili Wang, Soroush Vosoughi

Figure 1 for GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks
Figure 2 for GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks
Figure 3 for GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks
Figure 4 for GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks
* In EMNLP 2021 
  Access Paper or Ask Questions

A Fast PC Algorithm with Reversed-order Pruning and A Parallelization Strategy


Sep 10, 2021
Kai Zhang, Chao Tian, Kun Zhang, Todd Johnson, Xiaoqian Jiang

Figure 1 for A Fast PC Algorithm with Reversed-order Pruning and A Parallelization Strategy
Figure 2 for A Fast PC Algorithm with Reversed-order Pruning and A Parallelization Strategy
Figure 3 for A Fast PC Algorithm with Reversed-order Pruning and A Parallelization Strategy
Figure 4 for A Fast PC Algorithm with Reversed-order Pruning and A Parallelization Strategy
* 37 pages 
  Access Paper or Ask Questions

Federated Variational Learning for Anomaly Detection in Multivariate Time Series


Aug 29, 2021
Kai Zhang, Yushan Jiang, Lee Seversky, Chengtao Xu, Dahai Liu, Houbing Song

Figure 1 for Federated Variational Learning for Anomaly Detection in Multivariate Time Series
Figure 2 for Federated Variational Learning for Anomaly Detection in Multivariate Time Series
Figure 3 for Federated Variational Learning for Anomaly Detection in Multivariate Time Series
Figure 4 for Federated Variational Learning for Anomaly Detection in Multivariate Time Series
* Accepted paper in the IEEE 40th International Performance Computing and Communications Conference - IPCCC 2021 
  Access Paper or Ask Questions

Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer


Aug 24, 2021
Bencheng Yan, Pengjie Wang, Kai Zhang, Wei Lin, Kuang-Chih Lee, Jian Xu, Bo Zheng

Figure 1 for Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
Figure 2 for Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
Figure 3 for Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
Figure 4 for Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
* CIKM 2021, 5 pages; The first two authors contributed equally to this work 
  Access Paper or Ask Questions

SwinIR: Image Restoration Using Swin Transformer


Aug 23, 2021
Jingyun Liang, Jiezhang Cao, Guolei Sun, Kai Zhang, Luc Van Gool, Radu Timofte

Figure 1 for SwinIR: Image Restoration Using Swin Transformer
Figure 2 for SwinIR: Image Restoration Using Swin Transformer
Figure 3 for SwinIR: Image Restoration Using Swin Transformer
Figure 4 for SwinIR: Image Restoration Using Swin Transformer
* Sota results on classical/lightweight/real-world image SR, image denoising and JPEG compression artifact reduction. Code: https://github.com/JingyunLiang/SwinIR 
  Access Paper or Ask Questions

Learning to Detect: A Data-driven Approach for Network Intrusion Detection


Aug 18, 2021
Zachary Tauscher, Yushan Jiang, Kai Zhang, Jian Wang, Houbing Song

Figure 1 for Learning to Detect: A Data-driven Approach for Network Intrusion Detection
Figure 2 for Learning to Detect: A Data-driven Approach for Network Intrusion Detection
Figure 3 for Learning to Detect: A Data-driven Approach for Network Intrusion Detection
Figure 4 for Learning to Detect: A Data-driven Approach for Network Intrusion Detection
* Accepted paper in the IEEE 40th International Performance Computing and Communications Conference - IPCCC 2021 
  Access Paper or Ask Questions

Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks


Aug 18, 2021
Weicheng Ma, Kai Zhang, Renze Lou, Lili Wang, Soroush Vosoughi

Figure 1 for Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks
Figure 2 for Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks
Figure 3 for Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks
Figure 4 for Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks
* In ACL 2021 
  Access Paper or Ask Questions

SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation


Aug 18, 2021
Kai Zhang, Hao Qian, Qi Liu, Zhiqiang Zhang, Jun Zhou, Jianhui Ma, Enhong Chen

Figure 1 for SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation
Figure 2 for SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation
Figure 3 for SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation
* 5 pages, 3 figures 
  Access Paper or Ask Questions

Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution


Aug 11, 2021
Jingyun Liang, Guolei Sun, Kai Zhang, Luc Van Gool, Radu Timofte

Figure 1 for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
Figure 2 for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
Figure 3 for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
Figure 4 for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
* Accepted by ICCV2021. Code: https://github.com/JingyunLiang/MANet 
  Access Paper or Ask Questions

Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling


Aug 11, 2021
Jingyun Liang, Andreas Lugmayr, Kai Zhang, Martin Danelljan, Luc Van Gool, Radu Timofte

Figure 1 for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
Figure 2 for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
Figure 3 for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
Figure 4 for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
* Accepted by ICCV2021. Code: https://github.com/JingyunLiang/HCFlow 
  Access Paper or Ask Questions

Video Super-Resolution Transformer


Jun 12, 2021
Jiezhang Cao, Yawei Li, Kai Zhang, Luc Van Gool

Figure 1 for Video Super-Resolution Transformer
Figure 2 for Video Super-Resolution Transformer
Figure 3 for Video Super-Resolution Transformer
Figure 4 for Video Super-Resolution Transformer

  Access Paper or Ask Questions

LocalViT: Bringing Locality to Vision Transformers


Apr 12, 2021
Yawei Li, Kai Zhang, Jiezhang Cao, Radu Timofte, Luc Van Gool

Figure 1 for LocalViT: Bringing Locality to Vision Transformers
Figure 2 for LocalViT: Bringing Locality to Vision Transformers
Figure 3 for LocalViT: Bringing Locality to Vision Transformers
Figure 4 for LocalViT: Bringing Locality to Vision Transformers

  Access Paper or Ask Questions

PQA: Perceptual Question Answering


Apr 08, 2021
Yonggang Qi, Kai Zhang, Aneeshan Sain, Yi-Zhe Song

Figure 1 for PQA: Perceptual Question Answering
Figure 2 for PQA: Perceptual Question Answering
Figure 3 for PQA: Perceptual Question Answering
Figure 4 for PQA: Perceptual Question Answering
* Accepted by CVPR 2021 
  Access Paper or Ask Questions

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting


Apr 01, 2021
Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala, Noah Snavely

Figure 1 for PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting
Figure 2 for PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting
Figure 3 for PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting
Figure 4 for PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting
* Accepted to CVPR 2021; Project page: https://kai-46.github.io/PhySG-website/ 
  Access Paper or Ask Questions

Flow-based Kernel Prior with Application to Blind Super-Resolution


Mar 29, 2021
Jingyun Liang, Kai Zhang, Shuhang Gu, Luc Van Gool, Radu Timofte

Figure 1 for Flow-based Kernel Prior with Application to Blind Super-Resolution
Figure 2 for Flow-based Kernel Prior with Application to Blind Super-Resolution
Figure 3 for Flow-based Kernel Prior with Application to Blind Super-Resolution
Figure 4 for Flow-based Kernel Prior with Application to Blind Super-Resolution
* Accepted by CVPR2021. Code: https://github.com/JingyunLiang/FKP 
  Access Paper or Ask Questions

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution


Mar 25, 2021
Kai Zhang, Jingyun Liang, Luc Van Gool, Radu Timofte

Figure 1 for Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
Figure 2 for Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
Figure 3 for Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
Figure 4 for Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
* Code: https://github.com/cszn/BSRGAN 
  Access Paper or Ask Questions

Spatio-Temporal Data Mining for Aviation Delay Prediction


Mar 20, 2021
Kai Zhang, Yushan Jiang, Dahai Liu, Houbing Song

Figure 1 for Spatio-Temporal Data Mining for Aviation Delay Prediction
Figure 2 for Spatio-Temporal Data Mining for Aviation Delay Prediction
Figure 3 for Spatio-Temporal Data Mining for Aviation Delay Prediction
Figure 4 for Spatio-Temporal Data Mining for Aviation Delay Prediction

  Access Paper or Ask Questions

BEAUTY Powered BEAST


Mar 11, 2021
Kai Zhang, Zhigen Zhao, Wen Zhou

Figure 1 for BEAUTY Powered BEAST
Figure 2 for BEAUTY Powered BEAST
Figure 3 for BEAUTY Powered BEAST
Figure 4 for BEAUTY Powered BEAST

  Access Paper or Ask Questions

Local Change Point Detection and Signal Cleaning using EEMD with applications to Acoustic Shockwaves and Cardiac Signals


Mar 01, 2021
Kentaro Hoffman, Jonathan M. Lees, Kai Zhang

Figure 1 for Local Change Point Detection and Signal Cleaning using EEMD with applications to Acoustic Shockwaves and Cardiac Signals
Figure 2 for Local Change Point Detection and Signal Cleaning using EEMD with applications to Acoustic Shockwaves and Cardiac Signals
Figure 3 for Local Change Point Detection and Signal Cleaning using EEMD with applications to Acoustic Shockwaves and Cardiac Signals
Figure 4 for Local Change Point Detection and Signal Cleaning using EEMD with applications to Acoustic Shockwaves and Cardiac Signals

  Access Paper or Ask Questions

RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER


Feb 05, 2021
Lin Sun, Jiquan Wang, Kai Zhang, Yindu Su, Fangsheng Weng

Figure 1 for RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER
Figure 2 for RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER
Figure 3 for RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER
Figure 4 for RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER
* Accepted by AAAI2021 
  Access Paper or Ask Questions

Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network


Feb 01, 2021
Kai Zhang, Siddharth Karanth, Bela Patel, Robert Murphy, Xiaoqian Jiang

Figure 1 for Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network
Figure 2 for Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network
Figure 3 for Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network
Figure 4 for Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network
* In review 
  Access Paper or Ask Questions

Sub-sampled Cross-component Prediction for Emerging Video Coding Standards


Dec 30, 2020
Junru Li, Meng Wang, Li Zhang, Shiqi Wang, Kai Zhang, Shanshe Wang, Siwei Ma, Wen Gao

Figure 1 for Sub-sampled Cross-component Prediction for Emerging Video Coding Standards
Figure 2 for Sub-sampled Cross-component Prediction for Emerging Video Coding Standards
Figure 3 for Sub-sampled Cross-component Prediction for Emerging Video Coding Standards
Figure 4 for Sub-sampled Cross-component Prediction for Emerging Video Coding Standards

  Access Paper or Ask Questions