Picture for Xingyu Wan

Xingyu Wan

StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond

Add code
Jun 04, 2024
Viaarxiv icon

Towards Unified Multi-granularity Text Detection with Interactive Attention

Add code
May 30, 2024
Viaarxiv icon

Auxiliary Loss Adaptation for Image Inpainting

Add code
Nov 22, 2021
Figure 1 for Auxiliary Loss Adaptation for Image Inpainting
Figure 2 for Auxiliary Loss Adaptation for Image Inpainting
Figure 3 for Auxiliary Loss Adaptation for Image Inpainting
Figure 4 for Auxiliary Loss Adaptation for Image Inpainting
Viaarxiv icon

Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection

Add code
Dec 12, 2020
Figure 1 for Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection
Figure 2 for Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection
Figure 3 for Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection
Figure 4 for Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection
Viaarxiv icon

End-to-End Multi-Object Tracking with Global Response Map

Add code
Jul 13, 2020
Figure 1 for End-to-End Multi-Object Tracking with Global Response Map
Figure 2 for End-to-End Multi-Object Tracking with Global Response Map
Figure 3 for End-to-End Multi-Object Tracking with Global Response Map
Figure 4 for End-to-End Multi-Object Tracking with Global Response Map
Viaarxiv icon