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 Xiao Zhang

Xiao Zhang

A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation


Sep 16, 2021
Yiming Zhao, Xiao Zhang, Xinming Huang

Figure 1 for A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation
Figure 2 for A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation
Figure 3 for A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation
Figure 4 for A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation
* Submitted to ICRA'22, code link: https://github.com/placeforyiming/Divide-and-Merge-LiDAR-Panoptic-Cluster 
  Access Paper or Ask Questions

A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentation


Aug 21, 2021
Yiming Zhao, Xiao Zhang, Xinming Huang

Figure 1 for A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentation
Figure 2 for A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentation
Figure 3 for A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentation
Figure 4 for A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentation
* 1. A hybrid SOTA solution. 2. Accept by ICCV2021 Workshop on Traditional Computer Vision in the Age of Deep Learning. 3. Code: https://github.com/placeforyiming/ICCVW21-LiDAR-Panoptic-Segmentation-TradiCV-Survey-of-Point-Cloud-Cluster 
  Access Paper or Ask Questions

Incorporating Label Uncertainty in Understanding Adversarial Robustness


Jul 07, 2021
Xiao Zhang, David Evans

Figure 1 for Incorporating Label Uncertainty in Understanding Adversarial Robustness
Figure 2 for Incorporating Label Uncertainty in Understanding Adversarial Robustness
Figure 3 for Incorporating Label Uncertainty in Understanding Adversarial Robustness
Figure 4 for Incorporating Label Uncertainty in Understanding Adversarial Robustness
* 20 pages, 6 figures, 1 table 
  Access Paper or Ask Questions

To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels


Jun 25, 2021
Yuning Chai, Pei Sun, Jiquan Ngiam, Weiyue Wang, Benjamin Caine, Vijay Vasudevan, Xiao Zhang, Dragomir Anguelov

Figure 1 for To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels
Figure 2 for To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels
Figure 3 for To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels
Figure 4 for To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels
* CVPR 2021 
  Access Paper or Ask Questions

RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection


Jun 25, 2021
Pei Sun, Weiyue Wang, Yuning Chai, Gamaleldin Elsayed, Alex Bewley, Xiao Zhang, Cristian Sminchisescu, Dragomir Anguelov

Figure 1 for RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
Figure 2 for RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
Figure 3 for RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
Figure 4 for RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
* CVPR 2021 
  Access Paper or Ask Questions

Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples


Jun 20, 2021
Xuanyu Wu, Xuhong Li, Haoyi Xiong, Xiao Zhang, Siyu Huang, Dejing Dou

Figure 1 for Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Figure 2 for Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Figure 3 for Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Figure 4 for Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples

  Access Paper or Ask Questions

Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification


Jun 11, 2021
Xiao Zhang, Yixiao Ge, Yu Qiao, Hongsheng Li

Figure 1 for Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
Figure 2 for Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
Figure 3 for Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
Figure 4 for Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
* Accepted by CVPR2021 
  Access Paper or Ask Questions

Optimization Variance: Exploring Generalization Properties of DNNs


Jun 03, 2021
Xiao Zhang, Dongrui Wu, Haoyi Xiong, Bo Dai

Figure 1 for Optimization Variance: Exploring Generalization Properties of DNNs
Figure 2 for Optimization Variance: Exploring Generalization Properties of DNNs
Figure 3 for Optimization Variance: Exploring Generalization Properties of DNNs
Figure 4 for Optimization Variance: Exploring Generalization Properties of DNNs
* Work in progress 
  Access Paper or Ask Questions

DCAP: Deep Cross Attentional Product Network for User Response Prediction


May 18, 2021
Zekai Chen, Fangtian Zhong, Zhumin Chen, Xiao Zhang, Robert Pless, Xiuzhen Cheng

Figure 1 for DCAP: Deep Cross Attentional Product Network for User Response Prediction
Figure 2 for DCAP: Deep Cross Attentional Product Network for User Response Prediction
Figure 3 for DCAP: Deep Cross Attentional Product Network for User Response Prediction
Figure 4 for DCAP: Deep Cross Attentional Product Network for User Response Prediction
* 12 pages, 10 figures 
  Access Paper or Ask Questions

ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework


May 18, 2021
Zekai Chen, Maiwang Shi, Xiao Zhang, Haochao Ying

Figure 1 for ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework
Figure 2 for ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework
Figure 3 for ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework
Figure 4 for ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework
* 7 pages, 5 figures 
  Access Paper or Ask Questions

Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification


Apr 27, 2021
Yixiao Ge, Ching Lam Choi, Xiao Zhang, Peipei Zhao, Feng Zhu, Rui Zhao, Hongsheng Li

Figure 1 for Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Figure 2 for Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Figure 3 for Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Figure 4 for Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
* Project Page: https://geyixiao.com/projects/bake 
  Access Paper or Ask Questions

Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT


Apr 08, 2021
Zekai Chen, Dingshuo Chen, Zixuan Yuan, Xiuzhen Cheng, Xiao Zhang

Figure 1 for Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
Figure 2 for Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
Figure 3 for Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
Figure 4 for Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
* 12 pages, 5 figures 
  Access Paper or Ask Questions

Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces


Mar 24, 2021
Jack Prescott, Xiao Zhang, David Evans

Figure 1 for Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces
Figure 2 for Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces
Figure 3 for Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces
* ICLR 2021 
  Access Paper or Ask Questions

Interpretable Deep Learning: Interpretations, Interpretability, Trustworthiness, and Beyond


Mar 19, 2021
Xuhong Li, Haoyi Xiong, Xingjian Li, Xuanyu Wu, Xiao Zhang, Ji Liu, Jiang Bian, Dejing Dou

Figure 1 for Interpretable Deep Learning: Interpretations, Interpretability, Trustworthiness, and Beyond
Figure 2 for Interpretable Deep Learning: Interpretations, Interpretability, Trustworthiness, and Beyond
Figure 3 for Interpretable Deep Learning: Interpretations, Interpretability, Trustworthiness, and Beyond
Figure 4 for Interpretable Deep Learning: Interpretations, Interpretability, Trustworthiness, and Beyond

  Access Paper or Ask Questions

Multi-Task Time Series Forecasting With Shared Attention


Jan 24, 2021
Zekai Chen, Jiaze E, Xiao Zhang, Hao Sheng, Xiuzheng Cheng

Figure 1 for Multi-Task Time Series Forecasting With Shared Attention
Figure 2 for Multi-Task Time Series Forecasting With Shared Attention
Figure 3 for Multi-Task Time Series Forecasting With Shared Attention
Figure 4 for Multi-Task Time Series Forecasting With Shared Attention
* Accepted by ICDMW 2020 
  Access Paper or Ask Questions

Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction


Jan 18, 2021
Qiang Zhou, Jingjing Gu, Xinjiang Lu, Fuzhen Zhuang, Yanchao Zhao, Qiuhong Wang, Xiao Zhang

Figure 1 for Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction
Figure 2 for Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction
Figure 3 for Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction
Figure 4 for Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction
* Accepted by the 35th AAAI Conference on Artificial Intelligence (AAAI 2021) 
  Access Paper or Ask Questions

Guidance Module Network for Video Captioning


Dec 20, 2020
Xiao Zhang, Chunsheng Liu, Faliang Chang

Figure 1 for Guidance Module Network for Video Captioning
Figure 2 for Guidance Module Network for Video Captioning
Figure 3 for Guidance Module Network for Video Captioning
Figure 4 for Guidance Module Network for Video Captioning

  Access Paper or Ask Questions

Self-Supervised Visual Representation Learning from Hierarchical Grouping


Dec 05, 2020
Xiao Zhang, Michael Maire

Figure 1 for Self-Supervised Visual Representation Learning from Hierarchical Grouping
Figure 2 for Self-Supervised Visual Representation Learning from Hierarchical Grouping
Figure 3 for Self-Supervised Visual Representation Learning from Hierarchical Grouping
Figure 4 for Self-Supervised Visual Representation Learning from Hierarchical Grouping
* Accepted by NeurIPS 2020 
  Access Paper or Ask Questions

Semi-supervised Autoencoding Projective Dependency Parsing


Nov 02, 2020
Xiao Zhang, Dan Goldwasser

Figure 1 for Semi-supervised Autoencoding Projective Dependency Parsing
Figure 2 for Semi-supervised Autoencoding Projective Dependency Parsing
Figure 3 for Semi-supervised Autoencoding Projective Dependency Parsing
Figure 4 for Semi-supervised Autoencoding Projective Dependency Parsing
* COLING 2020 
  Access Paper or Ask Questions

Cross-Lingual Document Retrieval with Smooth Learning


Nov 02, 2020
Jiapeng Liu, Xiao Zhang, Dan Goldwasser, Xiao Wang

Figure 1 for Cross-Lingual Document Retrieval with Smooth Learning
Figure 2 for Cross-Lingual Document Retrieval with Smooth Learning
Figure 3 for Cross-Lingual Document Retrieval with Smooth Learning
Figure 4 for Cross-Lingual Document Retrieval with Smooth Learning
* COLING 2020 
  Access Paper or Ask Questions

Measuring Information Transfer in Neural Networks


Sep 16, 2020
Xiao Zhang, Xingjian Li, Dejing Dou, Ji Wu

Figure 1 for Measuring Information Transfer in Neural Networks
Figure 2 for Measuring Information Transfer in Neural Networks
Figure 3 for Measuring Information Transfer in Neural Networks
Figure 4 for Measuring Information Transfer in Neural Networks

  Access Paper or Ask Questions

Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient


Jul 25, 2020
Haonan Jia, Xiao Zhang, Jun Xu, Wei Zeng, Hao Jiang, Xiaohui Yan, Ji-Rong Wen

Figure 1 for Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient
Figure 2 for Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient
Figure 3 for Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient
Figure 4 for Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient
* 8 pages, 3 figures 
  Access Paper or Ask Questions

Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs


Apr 29, 2020
Xiao Zhang, Dongrui Wu

Figure 1 for Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
Figure 2 for Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
Figure 3 for Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
Figure 4 for Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
* 14 pages,11 figures 
  Access Paper or Ask Questions

Nearly Optimal Risk Bounds for Kernel K-Means


Mar 09, 2020
Yong Liu, Lizhong Ding, Hua Zhang, Wenqi Ren, Xiao Zhang, Shali Jiang, Xinwang Liu, Weiping Wang


  Access Paper or Ask Questions

Tiny Noise Can Make an EEG-Based Brain-Computer Interface Speller Output Anything


Mar 04, 2020
Xiao Zhang, Dongrui Wu, Lieyun Ding, Hanbin Luo, Chin-Teng Lin, Tzyy-Ping Jung, Ricardo Chavarriaga

Figure 1 for Tiny Noise Can Make an EEG-Based Brain-Computer Interface Speller Output Anything
Figure 2 for Tiny Noise Can Make an EEG-Based Brain-Computer Interface Speller Output Anything
Figure 3 for Tiny Noise Can Make an EEG-Based Brain-Computer Interface Speller Output Anything
Figure 4 for Tiny Noise Can Make an EEG-Based Brain-Computer Interface Speller Output Anything

  Access Paper or Ask Questions

Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models


Mar 01, 2020
Xiao Zhang, Jinghui Chen, Quanquan Gu, David Evans

Figure 1 for Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
Figure 2 for Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
Figure 3 for Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
Figure 4 for Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
* 14 pages, 2 figures, 5 tables, AISTATS final paper reformatted for readability 
  Access Paper or Ask Questions

Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization


Feb 26, 2020
Sicheng Zhu, Xiao Zhang, David Evans

Figure 1 for Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
Figure 2 for Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
Figure 3 for Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
Figure 4 for Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
* 18 pages, 6 figures 
  Access Paper or Ask Questions

Label-guided Learning for Text Classification


Feb 25, 2020
Xien Liu, Song Wang, Xiao Zhang, Xinxin You, Ji Wu, Dejing Dou

Figure 1 for Label-guided Learning for Text Classification
Figure 2 for Label-guided Learning for Text Classification
Figure 3 for Label-guided Learning for Text Classification
Figure 4 for Label-guided Learning for Text Classification

  Access Paper or Ask Questions