Alert button
Picture for Hanrong Ye

Hanrong Ye

Alert button

SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis

Nov 06, 2023
Hanrong Ye, Jason Kuen, Qing Liu, Zhe Lin, Brian Price, Dan Xu

Viaarxiv icon

TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts

Jul 28, 2023
Hanrong Ye, Dan Xu

Figure 1 for TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts
Figure 2 for TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts
Figure 3 for TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts
Figure 4 for TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts
Viaarxiv icon

Contrastive Multi-Task Dense Prediction

Jul 16, 2023
Siwei Yang, Hanrong Ye, Dan Xu

Figure 1 for Contrastive Multi-Task Dense Prediction
Figure 2 for Contrastive Multi-Task Dense Prediction
Figure 3 for Contrastive Multi-Task Dense Prediction
Figure 4 for Contrastive Multi-Task Dense Prediction
Viaarxiv icon

InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding

Jun 08, 2023
Hanrong Ye, Dan Xu

Figure 1 for InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding
Figure 2 for InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding
Figure 3 for InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding
Figure 4 for InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding
Viaarxiv icon

Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation

Apr 06, 2023
Hanrong Ye, Dan Xu

Figure 1 for Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation
Figure 2 for Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation
Viaarxiv icon

Inverted Pyramid Multi-task Transformer for Dense Scene Understanding

Mar 15, 2022
Hanrong Ye, Dan Xu

Figure 1 for Inverted Pyramid Multi-task Transformer for Dense Scene Understanding
Figure 2 for Inverted Pyramid Multi-task Transformer for Dense Scene Understanding
Figure 3 for Inverted Pyramid Multi-task Transformer for Dense Scene Understanding
Figure 4 for Inverted Pyramid Multi-task Transformer for Dense Scene Understanding
Viaarxiv icon

Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification

Jun 05, 2020
Hanrong Ye, Hong Liu, Fanyang Meng, Xia Li

Figure 1 for Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
Figure 2 for Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
Figure 3 for Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
Figure 4 for Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
Viaarxiv icon

Target Image Video Search Based on Local Features

Aug 11, 2018
Bochen Guan, Hanrong Ye, Hong Liu, William Sethares

Figure 1 for Target Image Video Search Based on Local Features
Figure 2 for Target Image Video Search Based on Local Features
Figure 3 for Target Image Video Search Based on Local Features
Figure 4 for Target Image Video Search Based on Local Features
Viaarxiv icon