papers

Publications (17)

cs.CV2021

LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation

Guoping Xu, Xingrong Wu, Xuan Zhang +1

Medical image segmentation plays an essential role in developing computer-assisted diagnosis and therapy systems, yet still faces many challenges. In the past few years, the popula…

eess.IV2024

DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation

Guoping Xu, Ximing Wu, Wentao Liao +3

Accurately segmenting lesions in ultrasound images is challenging due to the difficulty in distinguishing boundaries between lesions and surrounding tissues. While deep learning ha…

cs.CV2024

A SAM-guided and Match-based Semi-Supervised Segmentation Framework for Medical Imaging

Guoping Xu, Xiaoxue Qian, Hua Chieh Shao +3

This study introduces SAMatch, a SAM-guided Match-based framework for semi-supervised medical image segmentation, aimed at improving pseudo label quality in data-scarce scenarios.…

cs.CV2025

Segment Anything for Video: A Comprehensive Review of Video Object Segmentation and Tracking from Past to Future

Guoping Xu, Jayaram K. Udupa, Yajun Yu +4

Video Object Segmentation and Tracking (VOST) presents a complex yet critical challenge in computer vision, requiring robust integration of segmentation and tracking across tempora…

eess.IV2026

Adapting Segment Anything Model 3 for Concept-Driven Lesion Segmentation in Medical Images: An Experimental Study

Guoping Xu, Jayaram K. Udupa, Yubing Tong +5

Accurate lesion segmentation is essential in medical image analysis, yet most existing methods are designed for specific anatomical sites or imaging modalities, limiting their gene…

cs.CV2025

TSMS-SAM2: Multi-scale Temporal Sampling Augmentation and Memory-Splitting Pruning for Promptable Video Object Segmentation and Tracking in Surgical Scenarios

Guoping Xu, Hua-Chieh Shao, You Zhang

Promptable video object segmentation and tracking (VOST) has seen significant advances with the emergence of foundation models like Segment Anything Model 2 (SAM2); however, their…