Yupei Wang
YOU?
Author Swipe
View article: Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?
Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models? Open
Despite significant progress in multimodal language models (LMs), it remains unclear whether visual grounding enhances their understanding of embodied knowledge compared to text-only models. To address this question, we propose a novel emb…
View article: Gaussian-Driven Unsupervised Domain Adaptation Object Detection Transformer for Remote Sensing Imagery
Gaussian-Driven Unsupervised Domain Adaptation Object Detection Transformer for Remote Sensing Imagery Open
Domain shift can cause the detector to fail in adapting to the test data, resulting in sharp decline in detection performance. To address this issue, many unsupervised domain adaptation detection methods have been proposed to improve model…
View article: CMT-Eval: A Novel Chinese Multi-turn Dialogue Evaluation Dataset Addressing Real-world Conversational Challenges
CMT-Eval: A Novel Chinese Multi-turn Dialogue Evaluation Dataset Addressing Real-world Conversational Challenges Open
View article: Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?
Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models? Open
View article: Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals
Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals Open
While current Automated Essay Scoring (AES) methods demonstrate high scoring agreement with human raters, their decision-making mechanisms are not fully understood. Our proposed method, using counterfactual intervention assisted by Large L…
View article: DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment
DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment Open
Object detectors frequently encounter significant performance degradation when confronted with domain gaps between collected data (source domain) and data from real-world applications (target domain). To address this task, numerous unsuper…
View article: Study on the mechanism of excess void gas pressure in slopes under strong earthquake conditions
Study on the mechanism of excess void gas pressure in slopes under strong earthquake conditions Open
Under strong earthquake conditions, excess void gas pressure is generated in slopes with cavities (without water), which accelerates tension cracking at the edges of the cavities and thus promotes slope failure. In this paper, a generalise…
View article: Domain Adaptive Semantic Segmentation of Remote Sensing Images via Self-Training-Based Dual-Level Data Augmentation
Domain Adaptive Semantic Segmentation of Remote Sensing Images via Self-Training-Based Dual-Level Data Augmentation Open
Semantic segmentation models experience a significant performance degradation due to domain shifts between the source and target domains. This issue is particularly prevalent in remote sensing imagery, where a semantic segmentation model t…
View article: Study on the Correlation between Excess Cavity Gas Pressure and Dynamic Response in a Slope Cavity Under Strong Earthquake Conditions
Study on the Correlation between Excess Cavity Gas Pressure and Dynamic Response in a Slope Cavity Under Strong Earthquake Conditions Open
View article: Novel de novo mutation in <i>ZBTB20</i> in a Chinese Primrose syndrome family and a review of the literature
Novel de novo mutation in <i>ZBTB20</i> in a Chinese Primrose syndrome family and a review of the literature Open
Background Primrose syndrome is an autosomal dominant disorder characterized by craniofacial dysmorphism, mental retardation, developmental delay, progressive muscle atrophy and calcification of the earlobe due to a mutation in the ZBTB20 …
View article: Genetic analysis and literature review of a <scp>Poirier–Bienvenu</scp> neurodevelopmental syndrome family line caused by a de novo frameshift variant in <scp><i>CSNK2B</i></scp>
Genetic analysis and literature review of a <span>Poirier–Bienvenu</span> neurodevelopmental syndrome family line caused by a de novo frameshift variant in <span><i>CSNK2B</i></span> Open
Background Poirier–Bienvenu neurodevelopmental syndrome (POBINDS) is a rare autosomal dominant neurologic disorder caused by a heterozygous variant of CSNK2B , which is characterized by early onset epilepsy, hypotonia, varying degrees of i…
View article: MS-Net: A Multi-modal Self-supervised Network for Fine-Grained Classification of Aircraft in SAR Images
MS-Net: A Multi-modal Self-supervised Network for Fine-Grained Classification of Aircraft in SAR Images Open
Synthetic aperture radar (SAR) imaging technology is commonly used to provide 24-hour all-weather earth observation. However, it still has some drawbacks in SAR target classification, especially in fine-grained classification of aircraft: …
View article: Small-Scale Ship Detection for SAR Remote Sensing Images Based on Coordinate-Aware Mixed Attention and Spatial Semantic Joint Context
Small-Scale Ship Detection for SAR Remote Sensing Images Based on Coordinate-Aware Mixed Attention and Spatial Semantic Joint Context Open
With the rapid development of deep learning technology in recent years, convolutional neural networks have gained remarkable progress in SAR ship detection tasks. However, noise interference of the background and inadequate appearance feat…
View article: Identification of deep intronic variants of PAH in phenylketonuria using full-length gene sequencing
Identification of deep intronic variants of PAH in phenylketonuria using full-length gene sequencing Open
View article: Longitudinal hemoglobin trajectories and acute kidney injury in patients undergoing cardiac surgery: a retrospective cohort study
Longitudinal hemoglobin trajectories and acute kidney injury in patients undergoing cardiac surgery: a retrospective cohort study Open
Object The purpose of this study was to describe the longitudinal dynamic hemoglobin trajectories in patients undergoing cardiac surgery and to explore whether they provide a broader perspective in predicting AKI compared to traditional th…
View article: The spectrum of phenylalanine hydroxylase variants and genotype–phenotype correlation in phenylketonuria patients in Gansu, China
The spectrum of phenylalanine hydroxylase variants and genotype–phenotype correlation in phenylketonuria patients in Gansu, China Open
View article: An improved anchor-free SAR ship detection algorithm based on brain-inspired attention mechanism
An improved anchor-free SAR ship detection algorithm based on brain-inspired attention mechanism Open
As a computing platform that can deal with problems independently and adapt to different environments, the brain-inspired function is similar to the human brain, which can effectively make use of visual targets and their surrounding backgr…
View article: A Local-Sparse-Information-Aggregation Transformer with Explicit Contour Guidance for SAR Ship Detection
A Local-Sparse-Information-Aggregation Transformer with Explicit Contour Guidance for SAR Ship Detection Open
Ship detection in synthetic aperture radar (SAR) images has witnessed rapid development in recent years, especially after the adoption of convolutional neural network (CNN)-based methods. Recently, a transformer using self-attention and a …
View article: Case Report: A Novel GJB2 Missense Variant Inherited From the Low-Level Mosaic Mother in a Chinese Female With Palmoplantar Keratoderma With Deafness
Case Report: A Novel GJB2 Missense Variant Inherited From the Low-Level Mosaic Mother in a Chinese Female With Palmoplantar Keratoderma With Deafness Open
Dominant variants in the gap junction beta-2 ( GJB2 ) gene may lead to various degrees of syndromic hearing loss (SHL) which is manifest as sensorineural hearing impairment and hyperproliferative epidermal disorders, including palmoplantar…
View article: Three Variants Affecting Exon 1 of Ectodysplasin A Cause X-Linked Hypohidrotic Ectodermal Dysplasia: Clinical and Molecular Characteristics
Three Variants Affecting Exon 1 of Ectodysplasin A Cause X-Linked Hypohidrotic Ectodermal Dysplasia: Clinical and Molecular Characteristics Open
Background: Ectodysplasin A (EDA) variations are major pathogenic factors for hypohidrotic ectodermal dysplasia (HED), the most common form of ectodermal dysplasia (ED), characterized by hypotrichosis, hypohidrosis, hypodontia, and other o…
View article: Dynamic Range Compression Self-Adaption Method for SAR Image Based on Deep Learning
Dynamic Range Compression Self-Adaption Method for SAR Image Based on Deep Learning Open
The visualization of synthetic aperture radar (SAR) images involves the mapping of high dynamic range (HDR) amplitude values to gray levels for lower dynamic range (LDR) display devices. This dynamic range compression process determines th…
View article: An Adaptive Sample Assignment Strategy Based on Feature Enhancement for Ship Detection in SAR Images
An Adaptive Sample Assignment Strategy Based on Feature Enhancement for Ship Detection in SAR Images Open
Recently, ship detection in synthetic aperture radar (SAR) images has received extensive attention. Most of the current ship detectors preset dense anchor boxes to achieve spatial alignment with ground-truth (GT) objects. Then, the detecto…
View article: Identification of a novel <scp>ANK1</scp> mutation in hereditary spherocytosis co‐existing with <scp>BWS</scp>
Identification of a novel <span>ANK1</span> mutation in hereditary spherocytosis co‐existing with <span>BWS</span> Open
Background Beckwith–Wiedemann syndrome (BWS) is an inherited disorder affecting 1 in 10,500 to 13,700 newborns worldwide. The disease is caused in a vast majority of patients by a molecular defect in the imprinted chromosome 11p15.5. Hered…
View article: Motion-Guided Global–Local Aggregation Transformer Network for Precipitation Nowcasting
Motion-Guided Global–Local Aggregation Transformer Network for Precipitation Nowcasting Open
Nowadays deep learning-based weather radar echo extrapolation methods have competently improved nowcasting quality. Current pure convolutional or convolutional recurrent neural network-based extrapolation pipelines inherently struggle in c…
View article: Exploring the Molecular Mechanism of lncRNA–miRNA–mRNA Networks in Non-Syndromic Cleft Lip with or without Cleft Palate
Exploring the Molecular Mechanism of lncRNA–miRNA–mRNA Networks in Non-Syndromic Cleft Lip with or without Cleft Palate Open
The identified lncRNAs and the established ceRNA regulatory network provide novel insight into the pathogenesis of NSCL/P, therefore hold great promise in NSCL/P management in clinical practice.
View article: Dual Attention Feature Fusion and Adaptive Context for Accurate Segmentation of Very High-Resolution Remote Sensing Images
Dual Attention Feature Fusion and Adaptive Context for Accurate Segmentation of Very High-Resolution Remote Sensing Images Open
Land cover classification of high-resolution remote sensing images aims to obtain pixel-level land cover understanding, which is often modeled as semantic segmentation of remote sensing images. In recent years, convolutional network (CNN)-…
View article: Aberrant Bcl-x splicing in cancer: from molecular mechanism to therapeutic modulation
Aberrant Bcl-x splicing in cancer: from molecular mechanism to therapeutic modulation Open
View article: A fast three-phase synchronization technique with parallel structure
A fast three-phase synchronization technique with parallel structure Open
View article: Inhibition of Wnt signalling pathway by XAV939 enhances radiosensitivity in human cervical cancer HeLa cells
Inhibition of Wnt signalling pathway by XAV939 enhances radiosensitivity in human cervical cancer HeLa cells Open
Cervical cancer is the second most common malignant tumour threatening women's health. In recent years, heavy-ion beam therapy is becoming a newly emerging therapeutic mean of cancer; however, radio-resistance and radiation-induced damage …
View article: Bidirectional Grid Fusion Network for Accurate Land Cover Classification of High-Resolution Remote Sensing Images
Bidirectional Grid Fusion Network for Accurate Land Cover Classification of High-Resolution Remote Sensing Images Open
Land cover classification has achieved significant advances by employing deep convolutional network (ConvNet) based methods. Following the paradigm of learning deep models, land cover classification is modeled as semantic segmentation of v…