← Search

Shuxin Wang

10 accepted papers

2025

A Tip-Flexible Endoscope With Reconfigurable Baseline for Enhanced 3D Perception

RA-L 2025

Stereoscopic endoscopes are widely used in minimally invasive cardiac surgery, providing 3D information of the thoracic cavity through small incisions. However, current high-precision 3D perception methods often reduce the flexibility of the endoscope, limiting its field of view. This study proposes

Cited by 0SourceScholar
2025

HAR-former: Hybrid Transformer with an Adaptive Time-Frequency Representation Matrix for Long-Term Series Forecasting

AISTATS 2025poster

Time series forecasting is crucial across various fields such as economics, energy, transportation planning, and weather prediction. Nevertheless, accurately modeling real-world systems is challenging due to their inherent complexity and non-stationarity. Traditional methods, which often depend on h…

Cited by 0SourceScholar
2024

A Framework for Real-time Generation of Multi-directional Traversability Maps in Unstructured Environments

ICRA 2024poster

In complex unstructured environments, accurate terrain traversability analysis is a fundamental requirement for the successful execution of any movements of ground robots, especially given that terrain traversability often exhibits anisotropy. However, the difficulty in obtaining multi-directional t…

Cited by 1SourceScholar
2024

A Novel Robot Platform With Decoupled Stiffness Control for Endoscopic Surgery

RA-L 2024

Endoscopic robot has garnered significant attention for its ability to offer auxiliary traction and precise maneuverability. However, the low stiffness of its insertion tube makes it susceptible to deformation, which poses great challenges for precise control. Existing variable stiffness technologie

Cited by 3SourceScholar
2023

Source Localization for Extremely Large-Scale Antenna Arrays with Spatial Non-Stationarity

ICASSP 2023accepted

Extremely large-scale antenna array (ELAA) is a promising technique in 6G and autonomous driving thanks to its high spatial resolution. However, due to the extremely large array aperture, the sources may only "see" a portion of the array, called visibility region (VR). Since the information of VR is…

Cited by 0SourceScholar
2021

Alternative Baselines for Low-Shot 3D Medical Image Segmentation—An Atlas Perspective

AAAI 2021technical

Low-shot (one/few-shot) segmentation has attracted increasing attention as it works well with limited annotation. State-of-the-art low-shot segmentation methods on natural images usually focus on implicit representation learning for each novel class, such as learning prototypes, deriving guidance fe…

Cited by 5SourcePDFScholar
2020

LT-Net: Label Transfer by Learning Reversible Voxel-Wise Correspondence for One-Shot Medical Image Segmentation

CVPR 2020poster

We introduce a one-shot segmentation method to alleviate the burden of manual annotation for medical images. The main idea is to treat one-shot segmentation as a classical atlas-based segmentation problem, where voxel-wise correspondence from the atlas to the unlabelled data is learned. Subsequently…

Cited by 96PDFScholar