Yue Hu
YOU?
Author Swipe
View article: Reject or Not?: A Benchmark for Voice Assistant Query Rejection in Smart Home Scenario and an Improved Method Based on LLMs
Reject or Not?: A Benchmark for Voice Assistant Query Rejection in Smart Home Scenario and an Improved Method Based on LLMs Open
In smart-home voice assistant scenario, deciding whether to accept or reject a user query is the first step before any downstream processing. To address the limited query-rejection capability of current voice assistants, this paper present…
View article: A 15-cm giant splenic artery aneurysm: A rare clinical case
A 15-cm giant splenic artery aneurysm: A rare clinical case Open
View article: A Nonlinear Volterra Filtering Hybrid Image-Denoising Method Based on the Improved Bat Algorithm for Optimizing Kernel Parameters
A Nonlinear Volterra Filtering Hybrid Image-Denoising Method Based on the Improved Bat Algorithm for Optimizing Kernel Parameters Open
To address the issue of reducing noise in images containing mixed noise, a Volterra filtering method based on a Bat algorithm with velocity weight perturbation is proposed to optimize kernel parameters. The structural advantages of the Vol…
View article: Digital twinning of temperature fields for modular multilayer multiphase pipeline structures
Digital twinning of temperature fields for modular multilayer multiphase pipeline structures Open
The temperature field of oil and gas wells in the field of petroleum engineering presents a core problem and challenge in the digital twin framework due to its ultra-long-distance and highly variable structural characteristics. The varying…
View article: Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization
Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization Open
Transformer-based models have achieved remarkable success, but their core components, Transformer layers, are largely heuristics-driven and engineered from the bottom up, calling for a prototypical model with high interpretability and prac…
View article: JotlasNet: Joint tensor low-rank and attention-based sparse unrolling network for accelerating dynamic MRI
JotlasNet: Joint tensor low-rank and attention-based sparse unrolling network for accelerating dynamic MRI Open
View article: Compositionally gradient Al <sub>2</sub> O <sub>3</sub> –B <sub>4</sub> C/Al composites with interpenetrating structure and tailored properties via material extrusion-based additive manufacturing and pressure infiltration
Compositionally gradient Al <sub>2</sub> O <sub>3</sub> –B <sub>4</sub> C/Al composites with interpenetrating structure and tailored properties via material extrusion-based additive manufacturing and pressure infiltration Open
Traditional fabrication methods for metal–ceramic composites often struggle to achieve the level of control needed for material on-demand design and property optimisation, despite the potential for enhanced performance. This study presents…
View article: Clinical benefits of central pancreatectomy for a patient with pancreatic schwannoma and diabetes
Clinical benefits of central pancreatectomy for a patient with pancreatic schwannoma and diabetes Open
Schwannomas are tumors that originate from the glial cells of the nervous system and can occur on myelinated nerve fibers throughout the body, especially in the craniofacial region. However, pancreatic schwannomas are extremely rare. We re…
View article: Towards Heterogeneous Federated Graph Learning Via Structural Entropy and Prototype Aggregation
Towards Heterogeneous Federated Graph Learning Via Structural Entropy and Prototype Aggregation Open
View article: An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models
An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models Open
Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work \cite{yu2024white} proposed an information-theoretic objective function called Sparse Rate Reduc…
View article: Differentiable SVD based on Moore-Penrose Pseudoinverse for Inverse Imaging Problems
Differentiable SVD based on Moore-Penrose Pseudoinverse for Inverse Imaging Problems Open
Low-rank regularization-based deep unrolling networks have achieved remarkable success in various inverse imaging problems (IIPs). However, the singular value decomposition (SVD) is non-differentiable when duplicated singular values occur,…
View article: Digital twinning of temperature fields for modular multilayer multiphase pipeline structures
Digital twinning of temperature fields for modular multilayer multiphase pipeline structures Open
The temperature field of oil and gas wells in the field of petroleum engineering presents a core problem and challenge in the digital twin framework due to its ultra-long-distance and highly variable structural characteristics. The varying…
View article: Contents list
Contents list Open
View article: Tailoring Curcumin Ternary Complex Nanocrystals Via Microfluidic Mediated Assembly: Stability, Solubility, Bioaccessibility and Formation Mechanism
Tailoring Curcumin Ternary Complex Nanocrystals Via Microfluidic Mediated Assembly: Stability, Solubility, Bioaccessibility and Formation Mechanism Open
View article: The Impact of Information-Granularity and Prioritization on Patients’ Care Modality Choice
The Impact of Information-Granularity and Prioritization on Patients’ Care Modality Choice Open
View article: Deep Structure-Preserved Graph Embedding for Improved Mrf Reconstruction
Deep Structure-Preserved Graph Embedding for Improved Mrf Reconstruction Open
View article: Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service
Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service Open
Recent advances in vision-language pre-trained models (VLPs) have significantly increased visual understanding and cross-modal analysis capabilities. Companies have emerged to provide multi-modal Embedding as a Service (EaaS) based on VLPs…
View article: Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval Open
Different from Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent that…
View article: Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search
Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search Open
Cross-Modal sponsored search displays multi-modal advertisements (ads) when consumers look for desired products by natural language queries in search engines. Since multi-modal ads bring complementary details for query-ads matching, the ab…
View article: Tensor robust principal component analysis based on Bayesian Tucker decomposition for thermographic inspection
Tensor robust principal component analysis based on Bayesian Tucker decomposition for thermographic inspection Open
View article: Recovering lossless propagation of polaritons with synthesized complex frequency excitation
Recovering lossless propagation of polaritons with synthesized complex frequency excitation Open
Surface plasmon polaritons and phonon polaritons offer a means of surpassing the diffraction limit of conventional optics and facilitate efficient energy storage, local field enhancement, high sensitivities, benefitting from their subwavel…
View article: Nanoarray-Embedded Hierarchical Hydrophobic Surfaces for Enhancing Durable Dropwise Condensation
Nanoarray-Embedded Hierarchical Hydrophobic Surfaces for Enhancing Durable Dropwise Condensation Open
Liquid accretion control plays a key role across a wide range of industrial applications, such as anti-icing, power generation, sewage treatment, water desalination, and energy harvesting. In condensation system, durable dropwise condensat…
View article: Deep Low-Rank and Sparse Patch-Image Network for Infrared Dim and Small Target Detection
Deep Low-Rank and Sparse Patch-Image Network for Infrared Dim and Small Target Detection Open
The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
View article: Cystic Neoplasms of the Pancreas: Differential Diagnosis and Radiology Correlation
Cystic Neoplasms of the Pancreas: Differential Diagnosis and Radiology Correlation Open
Although the probability of pancreatic cystic neoplasms (PCNs) being detected is raising year by year, their differential diagnosis and individualized treatment are still a challenge in clinical work. PCNs are tumors containing cystic comp…
View article: Subpixel Temperature Estimation by Information Transfer With Adaptive Ensemble Extreme Learning Machine (IT-AEELM)
Subpixel Temperature Estimation by Information Transfer With Adaptive Ensemble Extreme Learning Machine (IT-AEELM) Open
The retrieval of land surface temperature (LST) using thermal infrared (TIR) data is important in many applications. However, TIR data usually suffer from low spatial resolution. We introduce a novel subpixel LST estimation model using the…
View article: Mechanical behavior and microstructure evolution of Ti-6Al-4V wire rod for producing aerospace fasteners
Mechanical behavior and microstructure evolution of Ti-6Al-4V wire rod for producing aerospace fasteners Open
The basic deformation parameters had a significant influence on the mechanical behaviour and microstructure evolution of a Ti-6Al-4V wire rod.Compression experiments were conducted to study the effect of the deformation temperatures (25-90…
View article: 3D Beamforming for Improving the Security of UAV-Enabled Mobile Relaying System
3D Beamforming for Improving the Security of UAV-Enabled Mobile Relaying System Open
In this paper, we consider an unmanned aerial vehicle (UAV)-enabled mobile relaying system consists of a ground control station (GCS), a high-mobility UAV for relaying, a destination, and an eavesdropper. To improve the security of the thr…
View article: A Generalized Structured Low-Rank Matrix Completion Algorithm for MR Image Recovery
A Generalized Structured Low-Rank Matrix Completion Algorithm for MR Image Recovery Open
Recent theory of mapping an image into a structured low-rank Toeplitz or Hankel matrix has become an effective method to restore images. In this paper, we introduce a generalized structured low-rank algorithm to recover images from their u…
View article: A Generalized Structured Low-Rank Matrix Completion Algorithm for MR Image Recovery
A Generalized Structured Low-Rank Matrix Completion Algorithm for MR Image Recovery Open
Recent theory of mapping an image into a structured low-rank Toeplitz or Hankel matrix has become an effective method to restore images. In this paper, we introduce a generalized structured low-rank algorithm to recover images from their u…
View article: Adaptive structured low rank algorithm for MR image recovery
Adaptive structured low rank algorithm for MR image recovery Open
We introduce an adaptive structured low rank algorithm to recover MR images from their undersampled Fourier coefficients. The image is modeled as a combination of a piecewise constant component and a piecewise linear component. The Fourier…