Alert button
Picture for Xin Wang

Xin Wang

Alert button

Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders

Oct 19, 2022
Xin Wang, Junichi Yamagishi

Figure 1 for Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders
Figure 2 for Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders
Figure 3 for Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders
Figure 4 for Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders
Viaarxiv icon

InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features

Oct 14, 2022
Mingfu Xue, Xin Wang, Yinghao Wu, Shifeng Ni, Yushu Zhang, Weiqiang Liu

Figure 1 for InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features
Figure 2 for InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features
Figure 3 for InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features
Figure 4 for InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features
Viaarxiv icon

GGViT:Multistream Vision Transformer Network in Face2Face Facial Reenactment Detection

Oct 12, 2022
Haotian Wu, Peipei Wang, Xin Wang, Ji Xiang, Rui Gong

Figure 1 for GGViT:Multistream Vision Transformer Network in Face2Face Facial Reenactment Detection
Figure 2 for GGViT:Multistream Vision Transformer Network in Face2Face Facial Reenactment Detection
Figure 3 for GGViT:Multistream Vision Transformer Network in Face2Face Facial Reenactment Detection
Figure 4 for GGViT:Multistream Vision Transformer Network in Face2Face Facial Reenactment Detection
Viaarxiv icon

Block Format Error Bounds and Optimal Block Size Selection

Oct 11, 2022
Ilya Soloveychik, Ilya Lyubomirsky, Xin Wang, Sudeep Bhoja

Figure 1 for Block Format Error Bounds and Optimal Block Size Selection
Figure 2 for Block Format Error Bounds and Optimal Block Size Selection
Figure 3 for Block Format Error Bounds and Optimal Block Size Selection
Figure 4 for Block Format Error Bounds and Optimal Block Size Selection
Viaarxiv icon

3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography

Oct 11, 2022
Lin Wang, Xiufen Ye, Donghao Zhang, Wanji He, Lie Ju, Yi Luo, Huan Luo, Xin Wang, Wei Feng, Kaimin Song, Xin Zhao, Zongyuan Ge

Figure 1 for 3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
Figure 2 for 3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
Figure 3 for 3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
Figure 4 for 3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
Viaarxiv icon

HetSyn: Speeding Up Local SGD with Heterogeneous Synchronization

Oct 06, 2022
Feng Zhu, Jingjing Zhang, Xin Wang

Figure 1 for HetSyn: Speeding Up Local SGD with Heterogeneous Synchronization
Figure 2 for HetSyn: Speeding Up Local SGD with Heterogeneous Synchronization
Figure 3 for HetSyn: Speeding Up Local SGD with Heterogeneous Synchronization
Figure 4 for HetSyn: Speeding Up Local SGD with Heterogeneous Synchronization
Viaarxiv icon

ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild

Oct 05, 2022
Xuechen Liu, Xin Wang, Md Sahidullah, Jose Patino, Héctor Delgado, Tomi Kinnunen, Massimiliano Todisco, Junichi Yamagishi, Nicholas Evans, Andreas Nautsch, Kong Aik Lee

Figure 1 for ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
Figure 2 for ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
Figure 3 for ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
Figure 4 for ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
Viaarxiv icon

Attention Augmented ConvNeXt UNet For Rectal Tumour Segmentation

Oct 01, 2022
Hongwei Wu, Junlin Wang, Xin Wang, Hui Nan, Yaxin Wang, Haonan Jing, Kaixuan Shi

Figure 1 for Attention Augmented ConvNeXt UNet For Rectal Tumour Segmentation
Figure 2 for Attention Augmented ConvNeXt UNet For Rectal Tumour Segmentation
Figure 3 for Attention Augmented ConvNeXt UNet For Rectal Tumour Segmentation
Figure 4 for Attention Augmented ConvNeXt UNet For Rectal Tumour Segmentation
Viaarxiv icon

Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval

Sep 28, 2022
Zheng Li, Caili Guo, Xin Wang, Zerun Feng, Jenq-Neng Hwang, Zhongtian Du

Figure 1 for Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
Figure 2 for Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
Figure 3 for Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
Figure 4 for Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
Viaarxiv icon

3D Matting: A Soft Segmentation Method Applied in Computed Tomography

Sep 16, 2022
Lin Wang, Xiufen Ye, Donghao Zhang, Wanji He, Lie Ju, Xin Wang, Wei Feng, Kaimin Song, Xin Zhao, Zongyuan Ge

Figure 1 for 3D Matting: A Soft Segmentation Method Applied in Computed Tomography
Figure 2 for 3D Matting: A Soft Segmentation Method Applied in Computed Tomography
Figure 3 for 3D Matting: A Soft Segmentation Method Applied in Computed Tomography
Figure 4 for 3D Matting: A Soft Segmentation Method Applied in Computed Tomography
Viaarxiv icon