Picture for Xingkui Zhu

Xingkui Zhu

MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks

Add code
Jun 07, 2024
Viaarxiv icon

Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis

Add code
Mar 03, 2024
Viaarxiv icon

PointMamba: A Simple State Space Model for Point Cloud Analysis

Add code
Feb 19, 2024
Viaarxiv icon

Turning a CLIP Model into a Scene Text Spotter

Add code
Aug 21, 2023
Viaarxiv icon

TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios

Add code
Aug 26, 2021
Figure 1 for TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
Figure 2 for TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
Figure 3 for TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
Figure 4 for TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
Viaarxiv icon