29 citations · 185 across the 47 of their papers we have counts for
47 papers
Radiology Report Generation for Low-Quality X-Ray Images
Hongze Zhu, Chen Hu, Jiaxuan Jiang +6
Vision-Language Models (VLMs) have significantly advanced automated Radiology Report Generation (RRG). However, existing methods implicitly assume high-quality inputs, overlooking…
M2StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splatting
Xingyu Miao, Xueqi Qiu, Haoran Duan +4
Conventional 3D style transfer methods rely on a fixed reference image to apply artistic patterns to 3D scenes. However, in practical applications such as virtual or augmented real…
Structure Observation Driven Image-Text Contrastive Learning for Computed Tomography Report Generation
Hong Liu, Dong Wei, Qiong Peng +4
Computed Tomography Report Generation (CTRG) aims to automate the clinical radiology reporting process, thereby reducing the workload of report writing and facilitating patient car…
MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models
Yuqing Lei, Yingjun Du, Yawen Huang +2
Vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization but remain sensitive to domain shifts at test time. Test-time prompt tuning (TPT) mitigates this…
X-ray Insights Unleashed: Pioneering the Enhancement of Multi-Label Long-Tail Data
Xinquan Yang, Jinheng Xie, Yawen Huang +6
Long-tailed pulmonary anomalies in chest radiography present formidable diagnostic challenges. Despite the recent strides in diffusion-based methods for enhancing the representatio…
A Hybrid Framework Bridging CNN and ViT based on Theory of Evidence for Diabetic Retinopathy Grading
Junlai Qiu, Yunzhu Chen, Hao Zheng +2
Diabetic retinopathy (DR) is a leading cause of vision loss among middle-aged and elderly people, which significantly impacts their daily lives and mental health. To improve the ef…
Robust Source-Free Domain Adaptation for Medical Image Segmentation based on Curriculum Learning
Ziqi Zhang, Yuexiang Li, Yawen Huang +6
Recent studies have uncovered a new research line, namely source-free domain adaptation, which adapts a model to target domains without using the source data. Such a setting can ad…
TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiency
Minye Shao, Xingyu Miao, Haoran Duan +7
3D medical image generation is essential for data augmentation and patient privacy, calling for reliable and efficient models suited for clinical practice. However, current methods…
Rethinking Brain Tumor Segmentation from the Frequency Domain Perspective
Minye Shao, Zeyu Wang, Haoran Duan +5
Precise segmentation of brain tumors, particularly contrast-enhancing regions visible in post-contrast MRI (areas highlighted by contrast agent injection), is crucial for accurate…
DGFamba: Learning Flow Factorized State Space for Visual Domain Generalization
Qi Bi, Jingjun Yi, Hao Zheng +4
Domain generalization aims to learn a representation from the source domain, which can be generalized to arbitrary unseen target domains. A fundamental challenge for visual domain…
A Survey on Industrial Anomaly Synthesis
Yanshu Wang, Xichen Xu, Jiaqi Liu +6
This paper presents a comprehensive review of industrial anomaly synthesis (IAS). Existing surveys on industrial anomalies mainly focus on anomaly detection, while IAS is typically…
SP-SLAM: Neural Real-Time Dense SLAM With Scene Priors
Zhen Hong, Bowen Wang, Haoran Duan +6
Neural implicit representations have recently shown promising progress in dense Simultaneous Localization And Mapping (SLAM). However, existing works have shortcomings in terms of…
URoadNet: Dual Sparse Attentive U-Net for Multiscale Road Network Extraction
Jie Song, Yue Sun, Ziyun Cai +3
The challenges of road network segmentation demand an algorithm capable of adapting to the sparse and irregular shapes, as well as the diverse context, which often leads traditiona…
Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation
Jingjun Yi, Qi Bi, Hao Zheng +5
The rapid development of Vision Foundation Model (VFM) brings inherent out-domain generalization for a variety of down-stream tasks. Among them, domain generalized semantic segment…
Prototype Correlation Matching and Class-Relation Reasoning for Few-Shot Medical Image Segmentation
Yumin Zhang, Hongliu Li, Yajun Gao +3
Few-shot medical image segmentation has achieved great progress in improving accuracy and efficiency of medical analysis in the biomedical imaging field. However, most existing met…
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…
AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion
Jie Hu, Yawen Huang, Yilin Lu +4
Anomaly synthesis is one of the effective methods to augment abnormal samples for training. However, current anomaly synthesis methods predominantly rely on texture information as…
Learning Long-form Video Prior via Generative Pre-Training
Jinheng Xie, Jiajun Feng, Zhaoxu Tian +8
Concepts involved in long-form videos such as people, objects, and their interactions, can be viewed as following an implicit prior. They are notably complex and continue to pose c…
NeRF2Points: Large-Scale Point Cloud Generation From Street Views' Radiance Field Optimization
Peng Tu, Xun Zhou, Mingming Wang +7
Neural Radiance Fields (NeRF) have emerged as a paradigm-shifting methodology for the photorealistic rendering of objects and environments, enabling the synthesis of novel viewpoin…
ConRF: Zero-shot Stylization of 3D Scenes with Conditioned Radiation Fields
Xingyu Miao, Yang Bai, Haoran Duan +4
Most of the existing works on arbitrary 3D NeRF style transfer required retraining on each single style condition. This work aims to achieve zero-shot controlled stylization in 3D…
CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video
Xingyu Miao, Yang Bai, Haoran Duan +4
The goal of our work is to generate high-quality novel views from monocular videos of complex and dynamic scenes. Prior methods, such as DynamicNeRF, have shown impressive performa…
Federated Learning via Input-Output Collaborative Distillation
Xuan Gong, Shanglin Li, Yuxiang Bao +6
Federated learning (FL) is a machine learning paradigm in which distributed local nodes collaboratively train a central model without sharing individually held private data. Existi…
Automatic view plane prescription for cardiac magnetic resonance imaging via supervision by spatial relationship between views
Dong Wei, Yawen Huang, Donghuan Lu +2
Background: View planning for the acquisition of cardiac magnetic resonance (CMR) imaging remains a demanding task in clinical practice. Purpose: Existing approaches to its automat…
UniHead: Unifying Multi-Perception for Detection Heads
Hantao Zhou, Rui Yang, Yachao Zhang +5
The detection head constitutes a pivotal component within object detectors, tasked with executing both classification and localization functions. Regrettably, the commonly used par…