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

Add to Chrome

Add to Firefox

Picture for Kai Chen

Kai Chen

DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement

Jul 12, 2021
Xiaohuai Le, Hongsheng Chen, Kai Chen, Jing Lu

Figure 1 for DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement

Figure 2 for DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement

Figure 3 for DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement

* 5 pages, 1 figure, accepted by Interspeech 2021

Access Paper or Ask Questions

K-Net: Towards Unified Image Segmentation

Jun 28, 2021
Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy

Figure 1 for K-Net: Towards Unified Image Segmentation

Figure 2 for K-Net: Towards Unified Image Segmentation

Figure 3 for K-Net: Towards Unified Image Segmentation

Figure 4 for K-Net: Towards Unified Image Segmentation

* Technical Report

Access Paper or Ask Questions

DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks

May 13, 2021
Yingzhe He, Guozhu Meng, Kai Chen, Jinwen He, Xingbo Hu

Figure 1 for DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks

Figure 2 for DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks

Figure 3 for DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks

Figure 4 for DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks

* 16 pages, 10 figures, conference

Access Paper or Ask Questions

NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting

Feb 10, 2021
Kai Chen, Guang Chen, Dan Xu, Lijun Zhang, Yuyao Huang, Alois Knoll

Figure 1 for NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting

Figure 2 for NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting

Figure 3 for NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting

Figure 4 for NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting

* 10 pages, 4 figures

Access Paper or Ask Questions

Reliable Probabilistic Face Embeddings in the Wild

Feb 09, 2021
Kai Chen, Qi Lv, Taihe Yi, Zhengming Yi

Figure 1 for Reliable Probabilistic Face Embeddings in the Wild

Figure 2 for Reliable Probabilistic Face Embeddings in the Wild

Figure 3 for Reliable Probabilistic Face Embeddings in the Wild

Figure 4 for Reliable Probabilistic Face Embeddings in the Wild

* 14 pages

Access Paper or Ask Questions

UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement

Dec 25, 2020
Yangyang Qu, Kai Chen, Chao Liu, Yongsheng Ou

Figure 1 for UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement

Figure 2 for UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement

Figure 3 for UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement

Figure 4 for UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement

Access Paper or Ask Questions

A Hierarchical Reasoning Graph Neural Network for The Automatic Scoring of Answer Transcriptions in Video Job Interviews

Dec 22, 2020
Kai Chen, Meng Niu, Qingcai Chen

Figure 1 for A Hierarchical Reasoning Graph Neural Network for The Automatic Scoring of Answer Transcriptions in Video Job Interviews

Figure 2 for A Hierarchical Reasoning Graph Neural Network for The Automatic Scoring of Answer Transcriptions in Video Job Interviews

Figure 3 for A Hierarchical Reasoning Graph Neural Network for The Automatic Scoring of Answer Transcriptions in Video Job Interviews

Figure 4 for A Hierarchical Reasoning Graph Neural Network for The Automatic Scoring of Answer Transcriptions in Video Job Interviews

* 9 pages, 2 figures

Access Paper or Ask Questions

Positional Encoding as Spatial Inductive Bias in GANs

Dec 09, 2020
Rui Xu, Xintao Wang, Kai Chen, Bolei Zhou, Chen Change Loy

Figure 1 for Positional Encoding as Spatial Inductive Bias in GANs

Figure 2 for Positional Encoding as Spatial Inductive Bias in GANs

Figure 3 for Positional Encoding as Spatial Inductive Bias in GANs

Figure 4 for Positional Encoding as Spatial Inductive Bias in GANs

* paper with appendix, project page: https://nbei.github.io/gan-pos-encoding.html

Access Paper or Ask Questions

CARAFE++: Unified Content-Aware ReAssembly of FEatures

Dec 07, 2020
Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin

Figure 1 for CARAFE++: Unified Content-Aware ReAssembly of FEatures

Figure 2 for CARAFE++: Unified Content-Aware ReAssembly of FEatures

Figure 3 for CARAFE++: Unified Content-Aware ReAssembly of FEatures

Figure 4 for CARAFE++: Unified Content-Aware ReAssembly of FEatures

* Technical Report. Extended journal version of the conference paper that appeared as arXiv:1905.02188

Access Paper or Ask Questions

FedEval: A Benchmark System with a Comprehensive Evaluation Model for Federated Learning

Nov 25, 2020
Di Chai, Leye Wang, Kai Chen, Qiang Yang

Figure 1 for FedEval: A Benchmark System with a Comprehensive Evaluation Model for Federated Learning

Figure 2 for FedEval: A Benchmark System with a Comprehensive Evaluation Model for Federated Learning

Figure 3 for FedEval: A Benchmark System with a Comprehensive Evaluation Model for Federated Learning

Figure 4 for FedEval: A Benchmark System with a Comprehensive Evaluation Model for Federated Learning

Access Paper or Ask Questions

Skewed Laplace Spectral Mixture kernels for long-term forecasting in Gaussian process

Nov 08, 2020
Kai Chen, Twan van Laarhoven, Elena Marchiori

Figure 1 for Skewed Laplace Spectral Mixture kernels for long-term forecasting in Gaussian process

Figure 2 for Skewed Laplace Spectral Mixture kernels for long-term forecasting in Gaussian process

Figure 3 for Skewed Laplace Spectral Mixture kernels for long-term forecasting in Gaussian process

Figure 4 for Skewed Laplace Spectral Mixture kernels for long-term forecasting in Gaussian process

* 13 pages, 29 figures

Access Paper or Ask Questions

Exploring the Generalizability of Spatio-Temporal Crowd Flow Prediction: Meta-Modeling and an Analytic Framework

Sep 20, 2020
Leye Wang, Di Chai, Xuanzhe Liu, Liyue Chen, Kai Chen

Figure 1 for Exploring the Generalizability of Spatio-Temporal Crowd Flow Prediction: Meta-Modeling and an Analytic Framework

Figure 2 for Exploring the Generalizability of Spatio-Temporal Crowd Flow Prediction: Meta-Modeling and an Analytic Framework

Figure 3 for Exploring the Generalizability of Spatio-Temporal Crowd Flow Prediction: Meta-Modeling and an Analytic Framework

Figure 4 for Exploring the Generalizability of Spatio-Temporal Crowd Flow Prediction: Meta-Modeling and an Analytic Framework

Access Paper or Ask Questions

Seesaw Loss for Long-Tailed Instance Segmentation

Aug 23, 2020
Jiaqi Wang, Wenwei Zhang, Yuhang Zang, Yuhang Cao, Jiangmiao Pang, Tao Gong, Kai Chen, Ziwei Liu, Chen Change Loy, Dahua Lin

Figure 1 for Seesaw Loss for Long-Tailed Instance Segmentation

Figure 2 for Seesaw Loss for Long-Tailed Instance Segmentation

Figure 3 for Seesaw Loss for Long-Tailed Instance Segmentation

* Technical Report for LVIS Challenge 2020 https://www.lvisdataset.org/challenge_2020

Access Paper or Ask Questions

FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning

Jul 21, 2020
Zhaoxiong Yang, Shuihai Hu, Kai Chen

Figure 1 for FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning

Figure 2 for FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning

Figure 3 for FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning

Figure 4 for FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning

Access Paper or Ask Questions

Divide-and-Shuffle Synchronization for Distributed Machine Learning

Jul 07, 2020
Weiyan Wang, Cengguang Zhang, Liu Yang, Jiacheng Xia, Kai Chen, Kun Tan

Figure 1 for Divide-and-Shuffle Synchronization for Distributed Machine Learning

Figure 2 for Divide-and-Shuffle Synchronization for Distributed Machine Learning

Figure 3 for Divide-and-Shuffle Synchronization for Distributed Machine Learning

Figure 4 for Divide-and-Shuffle Synchronization for Distributed Machine Learning

* 15 pages, 5 figures, NeurIPS 2020 under review

Access Paper or Ask Questions

Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet

May 15, 2020
Hongsheng Chen, Teng Xiang, Kai Chen, Jing Lu

Figure 1 for Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet

Figure 2 for Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet

Figure 3 for Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet

Figure 4 for Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet

* 5 pages, 3 figures

Access Paper or Ask Questions

Neural Data-to-Text Generation with Dynamic Content Planning

Apr 20, 2020
Kai Chen, Fayuan Li, Baotian Hu, Weihua Peng, Qingcai Chen, Hong Yu

Figure 1 for Neural Data-to-Text Generation with Dynamic Content Planning

Figure 2 for Neural Data-to-Text Generation with Dynamic Content Planning

Figure 3 for Neural Data-to-Text Generation with Dynamic Content Planning

Figure 4 for Neural Data-to-Text Generation with Dynamic Content Planning

* 25 pages, 1 figure and 6 tables

Access Paper or Ask Questions