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 Kun Zhou

Kun Zhou

Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals


Jul 18, 2021
Yutao Zhu, Jian-Yun Nie, Kun Zhou, Pan Du, Hao Jiang, Zhicheng Dou

Figure 1 for Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals
Figure 2 for Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals
Figure 3 for Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals
* Accepted by SIGIR 2021 
  Access Paper or Ask Questions

Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer


Jul 08, 2021
Zongyang Du, Berrak Sisman, Kun Zhou, Haizhou Li

Figure 1 for Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
Figure 2 for Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
Figure 3 for Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
Figure 4 for Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
* Submitted to ASRU 2021 
  Access Paper or Ask Questions

Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation


Jun 12, 2021
Hui Wang, Kun Zhou, Wayne Xin Zhao, Jingyuan Wang, Ji-Rong Wen

Figure 1 for Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation
Figure 2 for Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation
Figure 3 for Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation
Figure 4 for Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation
* 26 pages 
  Access Paper or Ask Questions

Emotional Voice Conversion: Theory, Databases and ESD


May 31, 2021
Kun Zhou, Berrak Sisman, Rui Liu, Haizhou Li

Figure 1 for Emotional Voice Conversion: Theory, Databases and ESD
Figure 2 for Emotional Voice Conversion: Theory, Databases and ESD
Figure 3 for Emotional Voice Conversion: Theory, Databases and ESD
Figure 4 for Emotional Voice Conversion: Theory, Databases and ESD
* Submitted to Speech Communication 
  Access Paper or Ask Questions

LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond


May 21, 2021
Wenbo Li, Kun Zhou, Lu Qi, Nianjuan Jiang, Jiangbo Lu, Jiaya Jia

Figure 1 for LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond
Figure 2 for LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond
Figure 3 for LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond
Figure 4 for LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond
* NeurIPS2020 
  Access Paper or Ask Questions

BERT4SO: Neural Sentence Ordering by Fine-tuning BERT


Apr 13, 2021
Yutao Zhu, Jian-Yun Nie, Kun Zhou, Shengchao Liu, Yabo Ling, Pan Du

Figure 1 for BERT4SO: Neural Sentence Ordering by Fine-tuning BERT
Figure 2 for BERT4SO: Neural Sentence Ordering by Fine-tuning BERT
Figure 3 for BERT4SO: Neural Sentence Ordering by Fine-tuning BERT
Figure 4 for BERT4SO: Neural Sentence Ordering by Fine-tuning BERT

  Access Paper or Ask Questions

Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training


Mar 31, 2021
Kun Zhou, Berrak Sisman, Haizhou Li

Figure 1 for Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training
Figure 2 for Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training
Figure 3 for Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training
Figure 4 for Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training
* Submitted to Interspeech 2021 
  Access Paper or Ask Questions

Best-Buddy GANs for Highly Detailed Image Super-Resolution


Mar 29, 2021
Wenbo Li, Kun Zhou, Lu Qi, Liying Lu, Nianjuan Jiang, Jiangbo Lu, Jiaya Jia

Figure 1 for Best-Buddy GANs for Highly Detailed Image Super-Resolution
Figure 2 for Best-Buddy GANs for Highly Detailed Image Super-Resolution
Figure 3 for Best-Buddy GANs for Highly Detailed Image Super-Resolution
Figure 4 for Best-Buddy GANs for Highly Detailed Image Super-Resolution

  Access Paper or Ask Questions

Learning Efficient Photometric Feature Transform for Multi-view Stereo


Mar 27, 2021
Kaizhang Kang, Cihui Xie, Ruisheng Zhu, Xiaohe Ma, Ping Tan, Hongzhi Wu, Kun Zhou

Figure 1 for Learning Efficient Photometric Feature Transform for Multi-view Stereo
Figure 2 for Learning Efficient Photometric Feature Transform for Multi-view Stereo
Figure 3 for Learning Efficient Photometric Feature Transform for Multi-view Stereo
Figure 4 for Learning Efficient Photometric Feature Transform for Multi-view Stereo

  Access Paper or Ask Questions

BASAR:Black-box Attack on Skeletal Action Recognition


Mar 19, 2021
Yunfeng Diao, Tianjia Shao, Yong-Liang Yang, Kun Zhou, He Wang

Figure 1 for BASAR:Black-box Attack on Skeletal Action Recognition
Figure 2 for BASAR:Black-box Attack on Skeletal Action Recognition
Figure 3 for BASAR:Black-box Attack on Skeletal Action Recognition
Figure 4 for BASAR:Black-box Attack on Skeletal Action Recognition
* Accepted in CVPR 2021 
  Access Paper or Ask Questions

Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack


Mar 18, 2021
He Wang, Feixiang He, Zhexi Peng, Tianjia Shao, Yong-Liang Yang, Kun Zhou, David Hogg

Figure 1 for Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
Figure 2 for Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
Figure 3 for Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
Figure 4 for Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
* Accepted in CVPR 2021. arXiv admin note: substantial text overlap with arXiv:1911.07107 
  Access Paper or Ask Questions

In-game Residential Home Planning via Visual Context-aware Global Relation Learning


Feb 23, 2021
Lijuan Liu, Yin Yang, Yi Yuan, Tianjia Shao, He Wang, Kun Zhou

Figure 1 for In-game Residential Home Planning via Visual Context-aware Global Relation Learning
Figure 2 for In-game Residential Home Planning via Visual Context-aware Global Relation Learning
Figure 3 for In-game Residential Home Planning via Visual Context-aware Global Relation Learning
Figure 4 for In-game Residential Home Planning via Visual Context-aware Global Relation Learning

  Access Paper or Ask Questions

One-shot Face Reenactment Using Appearance Adaptive Normalization


Feb 20, 2021
Guangming Yao, Yi Yuan, Tianjia Shao, Shuang Li, Shanqi Liu, Yong Liu, Mengmeng Wang, Kun Zhou

Figure 1 for One-shot Face Reenactment Using Appearance Adaptive Normalization
Figure 2 for One-shot Face Reenactment Using Appearance Adaptive Normalization
Figure 3 for One-shot Face Reenactment Using Appearance Adaptive Normalization
Figure 4 for One-shot Face Reenactment Using Appearance Adaptive Normalization
* 9 pages, 8 figures,3 tables ,Accepted by AAAI2021 
  Access Paper or Ask Questions

High-order Differentiable Autoencoder for Nonlinear Model Reduction


Feb 19, 2021
Siyuan Shen, Yang Yin, Tianjia Shao, He Wang, Chenfanfu Jiang, Lei Lan, Kun Zhou

Figure 1 for High-order Differentiable Autoencoder for Nonlinear Model Reduction
Figure 2 for High-order Differentiable Autoencoder for Nonlinear Model Reduction
Figure 3 for High-order Differentiable Autoencoder for Nonlinear Model Reduction
Figure 4 for High-order Differentiable Autoencoder for Nonlinear Model Reduction

  Access Paper or Ask Questions

Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation


Feb 05, 2021
Jilin Tang, Yi Yuan, Tianjia Shao, Yong Liu, Mengmeng Wang, Kun Zhou

Figure 1 for Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
Figure 2 for Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
Figure 3 for Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
Figure 4 for Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
* 9 pages, 8 figures 
  Access Paper or Ask Questions

Neural Sentence Ordering Based on Constraint Graphs


Jan 28, 2021
Yutao Zhu, Kun Zhou, Jian-Yun Nie, Shengchao Liu, Zhicheng Dou

Figure 1 for Neural Sentence Ordering Based on Constraint Graphs
Figure 2 for Neural Sentence Ordering Based on Constraint Graphs
Figure 3 for Neural Sentence Ordering Based on Constraint Graphs
Figure 4 for Neural Sentence Ordering Based on Constraint Graphs
* AAAI 2021 Camera Ready 
  Access Paper or Ask Questions

Content Selection Network for Document-grounded Retrieval-based Chatbots


Jan 21, 2021
Yutao Zhu, Jian-Yun Nie, Kun Zhou, Pan Du, Zhicheng Dou

Figure 1 for Content Selection Network for Document-grounded Retrieval-based Chatbots
Figure 2 for Content Selection Network for Document-grounded Retrieval-based Chatbots
Figure 3 for Content Selection Network for Document-grounded Retrieval-based Chatbots
Figure 4 for Content Selection Network for Document-grounded Retrieval-based Chatbots
* ECIR 2021 Camera Ready 
  Access Paper or Ask Questions

CRSLab: An Open-Source Toolkit for Building Conversational Recommender System


Jan 04, 2021
Kun Zhou, Xiaolei Wang, Yuanhang Zhou, Chenzhan Shang, Yuan Cheng, Wayne Xin Zhao, Yaliang Li, Ji-Rong Wen

Figure 1 for CRSLab: An Open-Source Toolkit for Building Conversational Recommender System
Figure 2 for CRSLab: An Open-Source Toolkit for Building Conversational Recommender System
Figure 3 for CRSLab: An Open-Source Toolkit for Building Conversational Recommender System
Figure 4 for CRSLab: An Open-Source Toolkit for Building Conversational Recommender System
* 8 pages 
  Access Paper or Ask Questions

VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech


Nov 03, 2020
Kun Zhou, Berrak Sisman, Haizhou Li

Figure 1 for VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech
Figure 2 for VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech
Figure 3 for VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech
Figure 4 for VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech
* Accepted by IEEE SLT 2021. arXiv admin note: text overlap with arXiv:2005.07025 
  Access Paper or Ask Questions

Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset


Oct 28, 2020
Kun Zhou, Berrak Sisman, Rui Liu, Haizhou Li

Figure 1 for Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset
Figure 2 for Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset
Figure 3 for Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset
Figure 4 for Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset
* Submitted to ICASSP 2021 
  Access Paper or Ask Questions

Towards Topic-Guided Conversational Recommender System


Oct 08, 2020
Kun Zhou, Yuanhang Zhou, Wayne Xin Zhao, Xiaoke Wang, Ji-Rong Wen

Figure 1 for Towards Topic-Guided Conversational Recommender System
Figure 2 for Towards Topic-Guided Conversational Recommender System
Figure 3 for Towards Topic-Guided Conversational Recommender System
Figure 4 for Towards Topic-Guided Conversational Recommender System
* 12 pages, Accepted by Coling2020 
  Access Paper or Ask Questions

Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network


Sep 25, 2020
Shuqing Bian, Xu Chen, Wayne Xin Zhao, Kun Zhou, Yupeng Hou, Yang Song, Tao Zhang, Ji-Rong Wen

Figure 1 for Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network
Figure 2 for Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network
Figure 3 for Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network
Figure 4 for Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network
* CIKM 2020 
  Access Paper or Ask Questions

Mesh Guided One-shot Face Reenactment using Graph Convolutional Networks


Sep 18, 2020
Guangming Yao, Yi Yuan, Tianjia Shao, Kun Zhou

Figure 1 for Mesh Guided One-shot Face Reenactment using Graph Convolutional Networks
Figure 2 for Mesh Guided One-shot Face Reenactment using Graph Convolutional Networks
Figure 3 for Mesh Guided One-shot Face Reenactment using Graph Convolutional Networks
Figure 4 for Mesh Guided One-shot Face Reenactment using Graph Convolutional Networks
* 9 pages, 8 figures,accepted by ACM MM2020 
  Access Paper or Ask Questions

Second-order Neural Network Training Using Complex-step Directional Derivative


Sep 15, 2020
Siyuan Shen, Tianjia Shao, Kun Zhou, Chenfanfu Jiang, Feng Luo, Yin Yang

Figure 1 for Second-order Neural Network Training Using Complex-step Directional Derivative
Figure 2 for Second-order Neural Network Training Using Complex-step Directional Derivative
Figure 3 for Second-order Neural Network Training Using Complex-step Directional Derivative
Figure 4 for Second-order Neural Network Training Using Complex-step Directional Derivative

  Access Paper or Ask Questions

Dynamic Future Net: Diversified Human Motion Generation


Aug 25, 2020
Wenheng Chen, He Wang, Yi Yuan, Tianjia Shao, Kun Zhou

Figure 1 for Dynamic Future Net: Diversified Human Motion Generation
Figure 2 for Dynamic Future Net: Diversified Human Motion Generation
Figure 3 for Dynamic Future Net: Diversified Human Motion Generation
Figure 4 for Dynamic Future Net: Diversified Human Motion Generation
* Accepted by ACMMM 2020 
  Access Paper or Ask Questions