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 Xin Wang

Xin Wang

Estimating the confidence of speech spoofing countermeasure


Oct 10, 2021
Xin Wang, Junichi Yamagishi

Figure 1 for Estimating the confidence of speech spoofing countermeasure
Figure 2 for Estimating the confidence of speech spoofing countermeasure
Figure 3 for Estimating the confidence of speech spoofing countermeasure
Figure 4 for Estimating the confidence of speech spoofing countermeasure
* Work in progress. Comments are welcome 
  Access Paper or Ask Questions

Orthogonal Graph Neural Networks


Sep 23, 2021
Kai Guo, Kaixiong Zhou, Xia Hu, Yu Li, Yi Chang, Xin Wang

Figure 1 for Orthogonal Graph Neural Networks
Figure 2 for Orthogonal Graph Neural Networks
Figure 3 for Orthogonal Graph Neural Networks
Figure 4 for Orthogonal Graph Neural Networks

  Access Paper or Ask Questions

Rapid detection and recognition of whole brain activity in a freely behaving Caenorhabditis elegans


Sep 23, 2021
Yuxiang Wu, Shang Wu, Xin Wang, Chengtian Lang, Quanshi Zhang, Quan Wen, Tianqi Xu

Figure 1 for Rapid detection and recognition of whole brain activity in a freely behaving Caenorhabditis elegans
Figure 2 for Rapid detection and recognition of whole brain activity in a freely behaving Caenorhabditis elegans
Figure 3 for Rapid detection and recognition of whole brain activity in a freely behaving Caenorhabditis elegans
Figure 4 for Rapid detection and recognition of whole brain activity in a freely behaving Caenorhabditis elegans

  Access Paper or Ask Questions

A Survey on Temporal Sentence Grounding in Videos


Sep 17, 2021
Xiaohan Lan, Yitian Yuan, Xin Wang, Zhi Wang, Wenwu Zhu

Figure 1 for A Survey on Temporal Sentence Grounding in Videos
Figure 2 for A Survey on Temporal Sentence Grounding in Videos
Figure 3 for A Survey on Temporal Sentence Grounding in Videos
Figure 4 for A Survey on Temporal Sentence Grounding in Videos
* 32 pages with 19 figures 
  Access Paper or Ask Questions

SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation


Sep 09, 2021
Xin Wang, Yasheng Wang, Fei Mi, Pingyi Zhou, Yao Wan, Xiao Liu, Li Li, Hao Wu, Jin Liu, Xin Jiang

Figure 1 for SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
Figure 2 for SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
Figure 3 for SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
Figure 4 for SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
* 9 pages, 3 figures, 5 tables 
  Access Paper or Ask Questions

Wanderlust: Online Continual Object Detection in the Real World


Sep 07, 2021
Jianren Wang, Xin Wang, Yue Shang-Guan, Abhinav Gupta

Figure 1 for Wanderlust: Online Continual Object Detection in the Real World
Figure 2 for Wanderlust: Online Continual Object Detection in the Real World
Figure 3 for Wanderlust: Online Continual Object Detection in the Real World
Figure 4 for Wanderlust: Online Continual Object Detection in the Real World
* ICCV 2021 
  Access Paper or Ask Questions

Robust Attentive Deep Neural Network for Exposing GAN-generated Faces


Sep 05, 2021
Hui Guo, Shu Hu, Xin Wang, Ming-Ching Chang, Siwei Lyu

Figure 1 for Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
Figure 2 for Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
Figure 3 for Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
Figure 4 for Robust Attentive Deep Neural Network for Exposing GAN-generated Faces

  Access Paper or Ask Questions

Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning


Sep 05, 2021
Yusen Wu, Hao Chen, Xin Wang, Chao Liu, Phuong Nguyen, Yelena Yesha

Figure 1 for Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning
Figure 2 for Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning
Figure 3 for Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning
Figure 4 for Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning
* 10 pages, 4 figures, conference 
  Access Paper or Ask Questions

The VoicePrivacy 2020 Challenge: Results and findings


Sep 01, 2021
Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Jose Patino, Brij Mohan Lal Srivastava, Paul-Gauthier Noé, Andreas Nautsch, Nicholas Evans, Junichi Yamagishi, Benjamin O'Brien, Anaïs Chanclu, Jean-François Bonastre, Massimiliano Todisco, Mohamed Maouche

Figure 1 for The VoicePrivacy 2020 Challenge: Results and findings
Figure 2 for The VoicePrivacy 2020 Challenge: Results and findings
Figure 3 for The VoicePrivacy 2020 Challenge: Results and findings
Figure 4 for The VoicePrivacy 2020 Challenge: Results and findings
* Submitted to the Special Issue on Voice Privacy (Computer Speech and Language Journal - Elsevier); under review 
  Access Paper or Ask Questions

ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection


Sep 01, 2021
Junichi Yamagishi, Xin Wang, Massimiliano Todisco, Md Sahidullah, Jose Patino, Andreas Nautsch, Xuechen Liu, Kong Aik Lee, Tomi Kinnunen, Nicholas Evans, Héctor Delgado

Figure 1 for ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
Figure 2 for ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
Figure 3 for ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
Figure 4 for ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
* Accepted to the ASVspoof 2021 Workshop 
  Access Paper or Ask Questions

ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan


Sep 01, 2021
Héctor Delgado, Nicholas Evans, Tomi Kinnunen, Kong Aik Lee, Xuechen Liu, Andreas Nautsch, Jose Patino, Md Sahidullah, Massimiliano Todisco, Xin Wang, Junichi Yamagishi

Figure 1 for ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan
* http://www.asvspoof.org 
  Access Paper or Ask Questions

Benchmarking and challenges in security and privacy for voice biometrics


Sep 01, 2021
Jean-Francois Bonastre, Hector Delgado, Nicholas Evans, Tomi Kinnunen, Kong Aik Lee, Xuechen Liu, Andreas Nautsch, Paul-Gauthier Noe, Jose Patino, Md Sahidullah, Brij Mohan Lal Srivastava, Massimiliano Todisco, Natalia Tomashenko, Emmanuel Vincent, Xin Wang, Junichi Yamagishi

Figure 1 for Benchmarking and challenges in security and privacy for voice biometrics
Figure 2 for Benchmarking and challenges in security and privacy for voice biometrics
Figure 3 for Benchmarking and challenges in security and privacy for voice biometrics
Figure 4 for Benchmarking and challenges in security and privacy for voice biometrics
* Submitted to the symposium of the ISCA Security & Privacy in Speech Communications (SPSC) special interest group 
  Access Paper or Ask Questions

Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces


Sep 01, 2021
Hui Guo, Shu Hu, Xin Wang, Ming-Ching Chang, Siwei Lyu

Figure 1 for Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces
Figure 2 for Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces
Figure 3 for Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces
Figure 4 for Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces

  Access Paper or Ask Questions

CLSEBERT: Contrastive Learning for Syntax Enhanced Code Pre-Trained Model


Aug 23, 2021
Xin Wang, Yasheng Wang, Pingyi Zhou, Fei Mi, Meng Xiao, Yadao Wang, Li Li, Xiao Liu, Hao Wu, Jin Liu, Xin Jiang

Figure 1 for CLSEBERT: Contrastive Learning for Syntax Enhanced Code Pre-Trained Model
Figure 2 for CLSEBERT: Contrastive Learning for Syntax Enhanced Code Pre-Trained Model
Figure 3 for CLSEBERT: Contrastive Learning for Syntax Enhanced Code Pre-Trained Model
Figure 4 for CLSEBERT: Contrastive Learning for Syntax Enhanced Code Pre-Trained Model
* 9 pages, 3 figures, 5 tables 
  Access Paper or Ask Questions

Interpreting Attributions and Interactions of Adversarial Attacks


Aug 16, 2021
Xin Wang, Shuyun Lin, Hao Zhang, Yufei Zhu, Quanshi Zhang

Figure 1 for Interpreting Attributions and Interactions of Adversarial Attacks
Figure 2 for Interpreting Attributions and Interactions of Adversarial Attacks
Figure 3 for Interpreting Attributions and Interactions of Adversarial Attacks
Figure 4 for Interpreting Attributions and Interactions of Adversarial Attacks

  Access Paper or Ask Questions

Distilling Holistic Knowledge with Graph Neural Networks


Aug 12, 2021
Sheng Zhou, Yucheng Wang, Defang Chen, Jiawei Chen, Xin Wang, Can Wang, Jiajun Bu

Figure 1 for Distilling Holistic Knowledge with Graph Neural Networks
Figure 2 for Distilling Holistic Knowledge with Graph Neural Networks
Figure 3 for Distilling Holistic Knowledge with Graph Neural Networks
Figure 4 for Distilling Holistic Knowledge with Graph Neural Networks
* Accepted by ICCV 2021 
  Access Paper or Ask Questions

Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization


Aug 04, 2021
Wei Feng, Lie Ju, Lin Wang, Kaimin Song, Xin Wang, Xin Zhao, Qingyi Tao, Zongyuan Ge

Figure 1 for Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
Figure 2 for Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
Figure 3 for Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
Figure 4 for Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization

  Access Paper or Ask Questions

Dynamic Multi-scale Convolution for Dialect Identification


Aug 02, 2021
Tianlong Kong, Shouyi Yin, Dawei Zhang, Wang Geng, Xin Wang, Dandan Song, Jinwen Huang, Huiyu Shi, Xiaorui Wang

Figure 1 for Dynamic Multi-scale Convolution for Dialect Identification
Figure 2 for Dynamic Multi-scale Convolution for Dialect Identification
Figure 3 for Dynamic Multi-scale Convolution for Dialect Identification
Figure 4 for Dynamic Multi-scale Convolution for Dialect Identification

  Access Paper or Ask Questions

A Hypothesis for the Aesthetic Appreciation in Neural Networks


Jul 31, 2021
Xu Cheng, Xin Wang, Haotian Xue, Zhengyang Liang, Quanshi Zhang

Figure 1 for A Hypothesis for the Aesthetic Appreciation in Neural Networks
Figure 2 for A Hypothesis for the Aesthetic Appreciation in Neural Networks
Figure 3 for A Hypothesis for the Aesthetic Appreciation in Neural Networks
Figure 4 for A Hypothesis for the Aesthetic Appreciation in Neural Networks

  Access Paper or Ask Questions

T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-Label Learning


Jul 31, 2021
Shu Hu, Lipeng Ke, Xin Wang, Siwei Lyu

Figure 1 for T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-Label Learning
Figure 2 for T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-Label Learning
Figure 3 for T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-Label Learning
Figure 4 for T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-Label Learning
* Accepted by International Conference on Computer Vision (ICCV 2021) (14 pages) 
  Access Paper or Ask Questions

High-Efficiency Resonant Beam Charging and Communication


Jul 30, 2021
Yunfeng Bai, Qingwen Liu, Xin Wang, Bin Zhou, Zhiyong Bu

Figure 1 for High-Efficiency Resonant Beam Charging and Communication
Figure 2 for High-Efficiency Resonant Beam Charging and Communication
Figure 3 for High-Efficiency Resonant Beam Charging and Communication
Figure 4 for High-Efficiency Resonant Beam Charging and Communication

  Access Paper or Ask Questions

ReFormer: The Relational Transformer for Image Captioning


Jul 29, 2021
Xuewen Yang, Yingru Liu, Xin Wang

Figure 1 for ReFormer: The Relational Transformer for Image Captioning
Figure 2 for ReFormer: The Relational Transformer for Image Captioning
Figure 3 for ReFormer: The Relational Transformer for Image Captioning
Figure 4 for ReFormer: The Relational Transformer for Image Captioning

  Access Paper or Ask Questions

Multi-Task Learning in Utterance-Level and Segmental-Level Spoof Detection


Jul 29, 2021
Lin Zhang, Xin Wang, Erica Cooper, Junichi Yamagishi

Figure 1 for Multi-Task Learning in Utterance-Level and Segmental-Level Spoof Detection
Figure 2 for Multi-Task Learning in Utterance-Level and Segmental-Level Spoof Detection
Figure 3 for Multi-Task Learning in Utterance-Level and Segmental-Level Spoof Detection
Figure 4 for Multi-Task Learning in Utterance-Level and Segmental-Level Spoof Detection
* Submitted to ASVspoof 2021 Workshop 
  Access Paper or Ask Questions

VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation


Jul 29, 2021
Zeyu Hu, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai

Figure 1 for VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation
Figure 2 for VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation
Figure 3 for VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation
Figure 4 for VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation
* ICCV2021(Oral), supplementary materials included 
  Access Paper or Ask Questions

Medical Matting: A New Perspective on Medical Segmentation with Uncertainty


Jul 08, 2021
Lin Wang, Lie Ju, Donghao Zhang, Xin Wang, Wanji He, Yelin Huang, Zhiwen Yang, Xuan Yao, Xin Zhao, Xiufen Ye, Zongyuan Ge

Figure 1 for Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
Figure 2 for Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
Figure 3 for Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
Figure 4 for Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
* 11 pages, 5 figures 
  Access Paper or Ask Questions

Multi-task Over-the-Air Federated Learning: A Non-Orthogonal Transmission Approach


Jun 29, 2021
Haoming Ma, Xiaojun Yuan, Dian Fan, Zhi Ding, Xin Wang

Figure 1 for Multi-task Over-the-Air Federated Learning: A Non-Orthogonal Transmission Approach
Figure 2 for Multi-task Over-the-Air Federated Learning: A Non-Orthogonal Transmission Approach
Figure 3 for Multi-task Over-the-Air Federated Learning: A Non-Orthogonal Transmission Approach
Figure 4 for Multi-task Over-the-Air Federated Learning: A Non-Orthogonal Transmission Approach

  Access Paper or Ask Questions

Mobile Optical Communications Using Second Harmonic of Intra-Cavity Laser


Jun 21, 2021
Mingliang Xiong, Qingwen Liu, Xin Wang, Shengli Zhou, Bin Zhou, Zhiyong Bu

Figure 1 for Mobile Optical Communications Using Second Harmonic of Intra-Cavity Laser
Figure 2 for Mobile Optical Communications Using Second Harmonic of Intra-Cavity Laser
Figure 3 for Mobile Optical Communications Using Second Harmonic of Intra-Cavity Laser
Figure 4 for Mobile Optical Communications Using Second Harmonic of Intra-Cavity Laser

  Access Paper or Ask Questions