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 Yan Xu

Yan Xu

PDNet: Towards Better One-stage Object Detection with Prediction Decoupling


Apr 28, 2021
Li Yang, Yan Xu, Shaoru Wang, Chunfeng Yuan, Ziqi Zhang, Bing Li, Weiming Hu

Figure 1 for PDNet: Towards Better One-stage Object Detection with Prediction Decoupling
Figure 2 for PDNet: Towards Better One-stage Object Detection with Prediction Decoupling
Figure 3 for PDNet: Towards Better One-stage Object Detection with Prediction Decoupling
Figure 4 for PDNet: Towards Better One-stage Object Detection with Prediction Decoupling

  Access Paper or Ask Questions

LIFE: Lighting Invariant Flow Estimation


Apr 19, 2021
Zhaoyang Huang, Xiaokun Pan, Runsen Xu, Yan Xu, Ka chun Cheung, Guofeng Zhang, Hongsheng Li

Figure 1 for LIFE: Lighting Invariant Flow Estimation
Figure 2 for LIFE: Lighting Invariant Flow Estimation
Figure 3 for LIFE: Lighting Invariant Flow Estimation
Figure 4 for LIFE: Lighting Invariant Flow Estimation
* Project page: https://drinkingcoder.github.io/publication/life/ 
  Access Paper or Ask Questions

Wide-Baseline Multi-Camera Calibration using Person Re-Identification


Apr 17, 2021
Yan Xu, Yu-Jhe Li, Xinshuo Weng, Kris Kitani

Figure 1 for Wide-Baseline Multi-Camera Calibration using Person Re-Identification
Figure 2 for Wide-Baseline Multi-Camera Calibration using Person Re-Identification
Figure 3 for Wide-Baseline Multi-Camera Calibration using Person Re-Identification
Figure 4 for Wide-Baseline Multi-Camera Calibration using Person Re-Identification

  Access Paper or Ask Questions

Semi-supervised Variational Temporal Convolutional Network for IoT Communication Multi-anomaly Detection


Apr 05, 2021
Yan Xu, Yongliang Cheng

Figure 1 for Semi-supervised Variational Temporal Convolutional Network for IoT Communication Multi-anomaly Detection
Figure 2 for Semi-supervised Variational Temporal Convolutional Network for IoT Communication Multi-anomaly Detection
Figure 3 for Semi-supervised Variational Temporal Convolutional Network for IoT Communication Multi-anomaly Detection
Figure 4 for Semi-supervised Variational Temporal Convolutional Network for IoT Communication Multi-anomaly Detection
* 9 pages, 6 figures 
  Access Paper or Ask Questions

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks


Mar 18, 2021
Shengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric I Chang, Yan Xu

Figure 1 for Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
Figure 2 for Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
Figure 3 for Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
Figure 4 for Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
* ICLR 2021 (Spotlight). Code: https://github.com/zsyzzsoft/co-mod-gan Demo: https://comodgan.ml/ 
  Access Paper or Ask Questions

CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results


Feb 26, 2021
Yuanhan Zhang, Zhenfei Yin, Jing Shao, Ziwei Liu, Shuo Yang, Yuanjun Xiong, Wei Xia, Yan Xu, Man Luo, Jian Liu, Jianshu Li, Zhijun Chen, Mingyu Guo, Hui Li, Junfu Liu, Pengfei Gao, Tianqi Hong, Hao Han, Shijie Liu, Xinhua Chen, Di Qiu, Cheng Zhen, Dashuang Liang, Yufeng Jin, Zhanlong Hao

Figure 1 for CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results
Figure 2 for CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results
Figure 3 for CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results
Figure 4 for CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results
* Technical report. Challenge website: https://competitions.codalab.org/competitions/26210 
  Access Paper or Ask Questions

CrossNER: Evaluating Cross-Domain Named Entity Recognition


Dec 13, 2020
Zihan Liu, Yan Xu, Tiezheng Yu, Wenliang Dai, Ziwei Ji, Samuel Cahyawijaya, Andrea Madotto, Pascale Fung

Figure 1 for CrossNER: Evaluating Cross-Domain Named Entity Recognition
Figure 2 for CrossNER: Evaluating Cross-Domain Named Entity Recognition
Figure 3 for CrossNER: Evaluating Cross-Domain Named Entity Recognition
Figure 4 for CrossNER: Evaluating Cross-Domain Named Entity Recognition
* Accepted in AAAI-2021 
  Access Paper or Ask Questions

SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks


Oct 19, 2020
Yan Xu, Zhaoyang Huang, Kwan-Yee Lin, Xinge Zhu, Jianping Shi, Hujun Bao, Guofeng Zhang, Hongsheng Li

Figure 1 for SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks
Figure 2 for SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks
Figure 3 for SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks
Figure 4 for SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks
* Accepted to CoRL 2020 
  Access Paper or Ask Questions

Multi-hop Question Generation with Graph Convolutional Network


Oct 19, 2020
Dan Su, Yan Xu, Wenliang Dai, Ziwei Ji, Tiezheng Yu, Pascale Fung

Figure 1 for Multi-hop Question Generation with Graph Convolutional Network
Figure 2 for Multi-hop Question Generation with Graph Convolutional Network
Figure 3 for Multi-hop Question Generation with Graph Convolutional Network
Figure 4 for Multi-hop Question Generation with Graph Convolutional Network

  Access Paper or Ask Questions

Microscopic fine-grained instance classification through deep attention


Oct 06, 2020
Mengran Fan, Tapabrata Chakrabort, Eric I-Chao Chang, Yan Xu, Jens Rittscher

Figure 1 for Microscopic fine-grained instance classification through deep attention
Figure 2 for Microscopic fine-grained instance classification through deep attention
Figure 3 for Microscopic fine-grained instance classification through deep attention
Figure 4 for Microscopic fine-grained instance classification through deep attention

  Access Paper or Ask Questions

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems


Sep 28, 2020
Andrea Madotto, Samuel Cahyawijaya, Genta Indra Winata, Yan Xu, Zihan Liu, Zhaojiang Lin, Pascale Fung

Figure 1 for Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems
Figure 2 for Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems
Figure 3 for Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems
Figure 4 for Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems
* Accepted EMNLP findings 
  Access Paper or Ask Questions

Few-Shot Learning with Intra-Class Knowledge Transfer


Aug 22, 2020
Vivek Roy, Yan Xu, Yu-Xiong Wang, Kris Kitani, Ruslan Salakhutdinov, Martial Hebert

Figure 1 for Few-Shot Learning with Intra-Class Knowledge Transfer
Figure 2 for Few-Shot Learning with Intra-Class Knowledge Transfer
Figure 3 for Few-Shot Learning with Intra-Class Knowledge Transfer
Figure 4 for Few-Shot Learning with Intra-Class Knowledge Transfer

  Access Paper or Ask Questions

Machine Learning in Heliophysics and Space Weather Forecasting: A White Paper of Findings and Recommendations


Jun 22, 2020
Gelu Nita, Manolis Georgoulis, Irina Kitiashvili, Viacheslav Sadykov, Enrico Camporeale, Alexander Kosovichev, Haimin Wang, Vincent Oria, Jason Wang, Rafal Angryk, Berkay Aydin, Azim Ahmadzadeh, Xiaoli Bai, Timothy Bastian, Soukaina Filali Boubrahimi, Bin Chen, Alisdair Davey, Sheldon Fereira, Gregory Fleishman, Dale Gary, Andrew Gerrard, Gregory Hellbourg, Katherine Herbert, Jack Ireland, Egor Illarionov, Natsuha Kuroda, Qin Li, Chang Liu, Yuexin Liu, Hyomin Kim, Dustin Kempton, Ruizhe Ma, Petrus Martens, Ryan McGranaghan, Edward Semones, John Stefan, Andrey Stejko, Yaireska Collado-Vega, Meiqi Wang, Yan Xu, Sijie Yu

* Workshop Report 
  Access Paper or Ask Questions

CAiRE-COVID: A Question Answering and Multi-Document Summarization System for COVID-19 Research


May 04, 2020
Dan Su, Yan Xu, Tiezheng Yu, Farhad Bin Siddique, Elham J. Barezi, Pascale Fung

Figure 1 for CAiRE-COVID: A Question Answering and Multi-Document Summarization System for COVID-19 Research
Figure 2 for CAiRE-COVID: A Question Answering and Multi-Document Summarization System for COVID-19 Research

  Access Paper or Ask Questions

A Natural Language Processing Pipeline of Chinese Free-text Radiology Reports for Liver Cancer Diagnosis


Apr 10, 2020
Honglei Liu, Yan Xu, Zhiqiang Zhang, Ni Wang, Yanqun Huang, Zhenghan Yang, Rui Jiang, Hui Chen

Figure 1 for A Natural Language Processing Pipeline of Chinese Free-text Radiology Reports for Liver Cancer Diagnosis
Figure 2 for A Natural Language Processing Pipeline of Chinese Free-text Radiology Reports for Liver Cancer Diagnosis
Figure 3 for A Natural Language Processing Pipeline of Chinese Free-text Radiology Reports for Liver Cancer Diagnosis
Figure 4 for A Natural Language Processing Pipeline of Chinese Free-text Radiology Reports for Liver Cancer Diagnosis
* 12Pages,4 Figures, 3 Tables 
  Access Paper or Ask Questions

MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask


Apr 08, 2020
Shengyu Zhao, Yilun Sheng, Yue Dong, Eric I-Chao Chang, Yan Xu

Figure 1 for MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
Figure 2 for MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
Figure 3 for MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
Figure 4 for MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
* CVPR 2020 (Oral) 
  Access Paper or Ask Questions

SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds


Apr 06, 2020
Xinge Zhu, Yuexin Ma, Tai Wang, Yan Xu, Jianping Shi, Dahua Lin

Figure 1 for SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
Figure 2 for SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
Figure 3 for SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
Figure 4 for SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
* Code is available at https://github.com/xinge008/SSN 
  Access Paper or Ask Questions

SiamSNN: Spike-based Siamese Network for Energy-Efficient and Real-time Object Tracking


Mar 17, 2020
Yihao Luo, Min Xu, Caihong Yuan, Xiang Cao, Yan Xu, Tianjiang Wang, Qi Feng

Figure 1 for SiamSNN: Spike-based Siamese Network for Energy-Efficient and Real-time Object Tracking
Figure 2 for SiamSNN: Spike-based Siamese Network for Energy-Efficient and Real-time Object Tracking
Figure 3 for SiamSNN: Spike-based Siamese Network for Energy-Efficient and Real-time Object Tracking
Figure 4 for SiamSNN: Spike-based Siamese Network for Energy-Efficient and Real-time Object Tracking
* 8pages 
  Access Paper or Ask Questions

Estimating 3D Camera Pose from 2D Pedestrian Trajectories


Jan 02, 2020
Yan Xu, Vivek Roy, Kris Kitani

Figure 1 for Estimating 3D Camera Pose from 2D Pedestrian Trajectories
Figure 2 for Estimating 3D Camera Pose from 2D Pedestrian Trajectories
Figure 3 for Estimating 3D Camera Pose from 2D Pedestrian Trajectories
Figure 4 for Estimating 3D Camera Pose from 2D Pedestrian Trajectories
* Accepted in WACV 2020 
  Access Paper or Ask Questions

Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables


Nov 11, 2019
Zihan Liu, Jamin Shin, Yan Xu, Genta Indra Winata, Peng Xu, Andrea Madotto, Pascale Fung

Figure 1 for Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables
Figure 2 for Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables
Figure 3 for Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables
Figure 4 for Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables
* Accepted in EMNLP 2019 
  Access Paper or Ask Questions

Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints


Oct 15, 2019
Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang, Hujun Bao, Hongsheng Li

Figure 1 for Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
Figure 2 for Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
Figure 3 for Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
Figure 4 for Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
* Accepted to ICCV 2019 
  Access Paper or Ask Questions

Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring


Aug 16, 2019
Zihan Liu, Yan Xu, Genta Indra Winata, Pascale Fung

Figure 1 for Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring
Figure 2 for Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring
Figure 3 for Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring
Figure 4 for Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring
* Accepted at WMT 2019. (The first and second authors contributed equally) 
  Access Paper or Ask Questions

Constrained Multi-Objective Optimization for Automated Machine Learning


Aug 14, 2019
Steven Gardner, Oleg Golovidov, Joshua Griffin, Patrick Koch, Wayne Thompson, Brett Wujek, Yan Xu

Figure 1 for Constrained Multi-Objective Optimization for Automated Machine Learning
Figure 2 for Constrained Multi-Objective Optimization for Automated Machine Learning
Figure 3 for Constrained Multi-Objective Optimization for Automated Machine Learning
Figure 4 for Constrained Multi-Objective Optimization for Automated Machine Learning
* 10 pages, 8 figures, accepted at DSAA 2019 
  Access Paper or Ask Questions

Recursive Cascaded Networks for Unsupervised Medical Image Registration


Jul 29, 2019
Shengyu Zhao, Yue Dong, Eric I-Chao Chang, Yan Xu

Figure 1 for Recursive Cascaded Networks for Unsupervised Medical Image Registration
Figure 2 for Recursive Cascaded Networks for Unsupervised Medical Image Registration
Figure 3 for Recursive Cascaded Networks for Unsupervised Medical Image Registration
Figure 4 for Recursive Cascaded Networks for Unsupervised Medical Image Registration
* Accepted to ICCV 2019 
  Access Paper or Ask Questions

CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification


Jun 10, 2019
Genta Indra Winata, Andrea Madotto, Zhaojiang Lin, Jamin Shin, Yan Xu, Peng Xu, Pascale Fung

Figure 1 for CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification
Figure 2 for CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification
Figure 3 for CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification
Figure 4 for CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification
* Accepted by SemEval 2019 
  Access Paper or Ask Questions

Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables


May 10, 2019
Yan Xu, Baoyuan Wu, Fumin Shen, Yanbo Fan, Yong Zhang, Heng Tao Shen, Wei Liu

Figure 1 for Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
Figure 2 for Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
Figure 3 for Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
Figure 4 for Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
* Accepted to CVPR 2019. Yan Xu and Baoyuan Wu are co-first authors 
  Access Paper or Ask Questions

Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network


Feb 13, 2019
Tingfung Lau, Ji Luo, Shengyu Zhao, Eric I-Chao Chang, Yan Xu

Figure 1 for Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network
Figure 2 for Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network
Figure 3 for Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network
Figure 4 for Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network

  Access Paper or Ask Questions