135 citations · 172 across the 11 of their papers we have counts for
12 papers
EndoPrior-GS: Dynamic Endoscopic Reconstruction with a Joint Texture Prior
Jiaqi Huang, Shidong Wang, Tong Xin +1
Dynamic endoscopic reconstruction is fundamental to robotic surgery and computer-assisted interventions. While 3D Gaussian Splatting (3DGS) realises real-time rendering, its applic…
SIEFormer: Spectral-Interpretable and -Enhanced Transformer for Generalized Category Discovery
Chunming Li, Shidong Wang, Tong Xin +1
This paper presents a novel approach, Spectral-Interpretable and -Enhanced Transformer (SIEFormer), which leverages spectral analysis to reinterpret the attention mechanism within…
Few-shot Novel Category Discovery
Chunming Li, Shidong Wang, Haofeng Zhang
The recently proposed Novel Category Discovery (NCD) adapt paradigm of transductive learning hinders its application in more real-world scenarios. In fact, few labeled data in part…
RobustEMD: Domain Robust Matching for Cross-domain Few-shot Medical Image Segmentation
Yazhou Zhu, Minxian Li, Qiaolin Ye +3
Few-shot medical image segmentation (FSMIS) aims to perform the limited annotated data learning in the medical image analysis scope. Despite the progress has been achieved, current…
Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning
Suyi Li, Chenyi Jiang, Shidong Wang +3
Compositional Zero-shot Learning (CZSL) aims to identify novel compositions via known attribute-object pairs. The primary challenge in CZSL tasks lies in the significant discrepanc…
Wearable-based behaviour interpolation for semi-supervised human activity recognition
Haoran Duan, Shidong Wang, Varun Ojha +5
While traditional feature engineering for Human Activity Recognition (HAR) involves a trial-anderror process, deep learning has emerged as a preferred method for high-level represe…
Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentation
Yazhou Zhu, Shidong Wang, Tong Xin +2
Few-shot Medical Image Segmentation (FSMIS) is a more promising solution for medical image segmentation tasks where high-quality annotations are naturally scarce. However, current…
Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer
Yazhou Zhu, Shidong Wang, Tong Xin +1
Automated segmentation of large volumes of medical images is often plagued by the limited availability of fully annotated data and the diversity of organ surface properties resulti…
Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning
Chenyi Jiang, Dubing Chen, Shidong Wang +3
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions from seen states and objects. The disparity between the manually labeled semantic information and its…
Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation
Xiaojie Zhao, Yuming Shen, Shidong Wang +1
The recent advance in deep generative models outlines a promising perspective in the realm of Zero-Shot Learning (ZSL). Most generative ZSL methods use category semantic attributes…
Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization
Shidong Wang, Yi Ren, Gerard Parr +2
Learning discriminative and invariant feature representation is the key to visual image categorization. In this article, we propose a novel invariant deep compressible covariance p…
Multi-Granularity Canonical Appearance Pooling for Remote Sensing Scene Classification
S. Wang, Y. Guan, L. Shao
Recognising remote sensing scene images remains challenging due to large visual-semantic discrepancies. These mainly arise due to the lack of detailed annotations that can be emplo…