Picture for Junhui Liu

Junhui Liu

FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter

Jun 12, 2024
Viaarxiv icon

Zero-Shot Emotion Transfer For Cross-Lingual Speech Synthesis

Add code
Oct 06, 2023
Figure 1 for Zero-Shot Emotion Transfer For Cross-Lingual Speech Synthesis
Figure 2 for Zero-Shot Emotion Transfer For Cross-Lingual Speech Synthesis
Figure 3 for Zero-Shot Emotion Transfer For Cross-Lingual Speech Synthesis
Figure 4 for Zero-Shot Emotion Transfer For Cross-Lingual Speech Synthesis
Viaarxiv icon

TKwinFormer: Top k Window Attention in Vision Transformers for Feature Matching

Add code
Aug 29, 2023
Figure 1 for TKwinFormer: Top k Window Attention in Vision Transformers for Feature Matching
Figure 2 for TKwinFormer: Top k Window Attention in Vision Transformers for Feature Matching
Figure 3 for TKwinFormer: Top k Window Attention in Vision Transformers for Feature Matching
Figure 4 for TKwinFormer: Top k Window Attention in Vision Transformers for Feature Matching
Viaarxiv icon

A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools

Jun 15, 2023
Figure 1 for A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools
Figure 2 for A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools
Figure 3 for A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools
Figure 4 for A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools
Viaarxiv icon

Preserving background sound in noise-robust voice conversion via multi-task learning

Add code
Nov 06, 2022
Figure 1 for Preserving background sound in noise-robust voice conversion via multi-task learning
Figure 2 for Preserving background sound in noise-robust voice conversion via multi-task learning
Figure 3 for Preserving background sound in noise-robust voice conversion via multi-task learning
Figure 4 for Preserving background sound in noise-robust voice conversion via multi-task learning
Viaarxiv icon

ClothFormer:Taming Video Virtual Try-on in All Module

Add code
Apr 26, 2022
Figure 1 for ClothFormer:Taming Video Virtual Try-on in All Module
Figure 2 for ClothFormer:Taming Video Virtual Try-on in All Module
Figure 3 for ClothFormer:Taming Video Virtual Try-on in All Module
Figure 4 for ClothFormer:Taming Video Virtual Try-on in All Module
Viaarxiv icon

Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solution

Add code
Apr 13, 2022
Figure 1 for Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solution
Figure 2 for Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solution
Figure 3 for Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solution
Figure 4 for Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solution
Viaarxiv icon

Boundary Content Graph Neural Network for Temporal Action Proposal Generation

Aug 04, 2020
Figure 1 for Boundary Content Graph Neural Network for Temporal Action Proposal Generation
Figure 2 for Boundary Content Graph Neural Network for Temporal Action Proposal Generation
Figure 3 for Boundary Content Graph Neural Network for Temporal Action Proposal Generation
Figure 4 for Boundary Content Graph Neural Network for Temporal Action Proposal Generation
Viaarxiv icon

Cross-modal supervised learning for better acoustic representations

Add code
Jan 01, 2020
Figure 1 for Cross-modal supervised learning for better acoustic representations
Figure 2 for Cross-modal supervised learning for better acoustic representations
Figure 3 for Cross-modal supervised learning for better acoustic representations
Figure 4 for Cross-modal supervised learning for better acoustic representations
Viaarxiv icon

Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition

Oct 24, 2019
Figure 1 for Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition
Figure 2 for Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition
Figure 3 for Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition
Figure 4 for Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition
Viaarxiv icon