Jianwei Zheng
YOU?
Author Swipe
View article: Novel Catalyst of NiFe‐LDO Layered Double for Efficient Deoxygenation of Palm Oil to Diesel‐Range Alkane
Novel Catalyst of NiFe‐LDO Layered Double for Efficient Deoxygenation of Palm Oil to Diesel‐Range Alkane Open
To achieve palm oil conversion along with a high yield of long‐chain alkane, a series of NiFe layered double oxide catalysts were prepared and employed in the deoxygenation of palm oil. The layered structure of these catalysts was confirme…
View article: Controllable Face Inpainting via Pseudo-Style Embedding
Controllable Face Inpainting via Pseudo-Style Embedding Open
Image inpainting, a critical facet of computer vision, is in full bloom accompanied by the rapid innovation of convolution neural networks and transformers, revolutionizing the practical management of abnormity disposal, image editing, etc…
View article: Gradient Selection Tuning via Information Bottleneck
Gradient Selection Tuning via Information Bottleneck Open
Pre-trained visual models enjoy strong representations, yet suffer from massive parameters to be shifted in downstream practices. Many parameter-efficient fine-tuning methods have been proposed, mostly requiring only 1% additional paramete…
View article: Curing Semantic Drift: A Dynamic Approach to Grounding Generation in Large Vision-Language Models
Curing Semantic Drift: A Dynamic Approach to Grounding Generation in Large Vision-Language Models Open
Large Vision-Language Models (LVLMs) face a tug-of-war between powerful linguistic priors and visual evidence, often leading to ``semantic drift'' -- the progressive detachment from visual input that we identify as the root cause of halluc…
View article: Breaking Information Isolation: Accelerating MRI via Inter-sequence Mapping and Progressive Masking
Breaking Information Isolation: Accelerating MRI via Inter-sequence Mapping and Progressive Masking Open
Deep unfolding network (DUN) has shed new light on multi-sequence MRI reconstruction, providing both high interpretability and acceptable performance. However, current approaches still suffer from the plight of information isolation, i.e.,…
View article: Axial-shunted Spatial-temporal Conversation for Change Detection
Axial-shunted Spatial-temporal Conversation for Change Detection Open
Benefitting from the maturing of intelligence techniques and advanced sensors, recent years have witnessed the full flourishing of change detection (CD) on multi-temporal remote sensing images. However, extraneous interference caused by no…
View article: Information-Coupled Neural Operator for Computational Mechanics and Parametric PDEs
Information-Coupled Neural Operator for Computational Mechanics and Parametric PDEs Open
View article: Theoretical study on the mechanism of stick-slip instability occurrence on deep coal-rock structure
Theoretical study on the mechanism of stick-slip instability occurrence on deep coal-rock structure Open
Dynamic disasters seriously threaten the safety and effectiveness in deep mining. The mechanism of stick-slip instability occurrence on the deep coal-rock structure was studied in this paper through analyzing the occurrence condition of st…
View article: Null Space Matters: Range-Null Decomposition for Consistent Multi-Contrast MRI Reconstruction
Null Space Matters: Range-Null Decomposition for Consistent Multi-Contrast MRI Reconstruction Open
Consistency and interpretability have long been the critical issues in MRI reconstruction. While interpretability has been dramatically improved with the employment of deep unfolding networks (DUNs), current methods still suffer from incon…
View article: SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting
SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting Open
Image inpainting is in full bloom accompanied by the progress of convolutional neural networks (CNNs) and transformers, revolutionizing the practical management of abnormity disposal, image editing, etc. However, due to the ever-mounting i…
View article: Information-Coupled MRI Acceleration Via Multi-Modal Mapping and Progressive Masking
Information-Coupled MRI Acceleration Via Multi-Modal Mapping and Progressive Masking Open
View article: Collaborative Cross-Complementary Unfolding Network for Pan-Sharpening Remote Sensing Image
Collaborative Cross-Complementary Unfolding Network for Pan-Sharpening Remote Sensing Image Open
View article: High-fidelity Person-centric Subject-to-Image Synthesis
High-fidelity Person-centric Subject-to-Image Synthesis Open
Current subject-driven image generation methods encounter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person generation by fine-tuning a common pre-trained diffusion, whic…
View article: Self-rated health and its related influencing factors among emergency department physicians: a national cross-sectional study
Self-rated health and its related influencing factors among emergency department physicians: a national cross-sectional study Open
Background Protecting and improving the personal health of healthcare workers is critical to improving the efficiency and quality of care. To effectively meet the needs of the emergency service system, emergency physicians need to be in a …
View article: Gene therapy: an emerging therapy for hair cells regeneration in the cochlea
Gene therapy: an emerging therapy for hair cells regeneration in the cochlea Open
Sensorineural hearing loss is typically caused by damage to the cochlear hair cells (HCs) due to external stimuli or because of one’s genetic factors and the inability to convert sound mechanical energy into nerve impulses. Adult mammalian…
View article: GA-HQS: MRI reconstruction via a generically accelerated unfolding approach
GA-HQS: MRI reconstruction via a generically accelerated unfolding approach Open
Deep unfolding networks (DUNs) are the foremost methods in the realm of compressed sensing MRI, as they can employ learnable networks to facilitate interpretable forward-inference operators. However, several daunting issues still exist, in…
View article: Hyperspectral Image Superresolution via Subspace-Based Deep Prior Regularization
Hyperspectral Image Superresolution via Subspace-Based Deep Prior Regularization Open
Hyperspectral imaging is able to provide a finer delivery of various material properties than conventional imaging systems. Yet in reality, an optical system can only generate data with high spatial resolution but low spectral one, or vice…
View article: Dense Vehicle Counting Estimation via a Synergism Attention Network
Dense Vehicle Counting Estimation via a Synergism Attention Network Open
Along with rising traffic jams, accurate counting of vehicles in surveillance images is becoming increasingly difficult. Current counting methods based on density maps have achieved tremendous improvement due to the prosperity of convoluti…
View article: WebAssembly-based Delta Sync for Cloud Storage Services
WebAssembly-based Delta Sync for Cloud Storage Services Open
Delta synchronization (sync) is crucial to the network-level efficiency of cloud storage services, especially when handling large files with small increments. Practical delta sync techniques are, however, only available for PC clients and …
View article: Cascading Blend Network for Image Inpainting
Cascading Blend Network for Image Inpainting Open
View article: Hyperspectral and Multispectral Data Fusion via Joint Local-Nonlocal Modeling and Truncation Operator
Hyperspectral and Multispectral Data Fusion via Joint Local-Nonlocal Modeling and Truncation Operator Open
Fusion technology has been the core strategy to obtain a high-spatial-spectral resolution hyperspectral image (HSI). In recent years, few fusion models focused on exploiting the underlying manifold structure in the spatial dimension of the…
View article: 3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples
3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples Open
Owing to the outstanding feature extraction capability, convolutional neural networks (CNNs) have been widely applied in hyperspectral image (HSI) classification problems and have achieved an impressive performance. However, it is well kno…
View article: Manifold-Based Nonlocal Second-Order Regularization for Hyperspectral Image Inpainting
Manifold-Based Nonlocal Second-Order Regularization for Hyperspectral Image Inpainting Open
The low-dimensional manifold of image patches has been introduced as regularizer term, and shown effective in hyperspectral image inpainting. However, in this article, we find that using only the low-dimensional property of manifold may no…
View article: Moreau-Enhanced Total Variation and Subspace Factorization for Hyperspectral Denoising
Moreau-Enhanced Total Variation and Subspace Factorization for Hyperspectral Denoising Open
Hyperspectral images (HSIs) denoising aims at recovering noise-free images from noisy counterparts to improve image visualization. Recently, various prior knowledge has attracted much attention in HSI denoising, e.g., total variation (TV),…
View article: Towards Adversarial Robustness via Feature Matching
Towards Adversarial Robustness via Feature Matching Open
Image classification systems are known to be vulnerable to adversarial attacks, which are imperceptibly perturbed but lead to spectacularly disgraceful classification. Adversarial training is one of the most effective defenses for improvin…
View article: Low-Rank Tensor Completion and Total Variation Minimization for Color Image Inpainting
Low-Rank Tensor Completion and Total Variation Minimization for Color Image Inpainting Open
Low-rank (LR) and total variation (TV) are two most frequent priors that occur in image processing problems, and they have sparked a tremendous amount of researches, particularly for moving from scalar to vector, matrix or even high-order …
View article: Perceptual Adversarial Networks With a Feature Pyramid for Image Translation
Perceptual Adversarial Networks With a Feature Pyramid for Image Translation Open
This paper investigates the image-to-image translations problems, where the input image is translated into its synthetic form with the original structure and semantics preserved. Widely used methods compute the pixel-wise MSE loss, which a…
View article: Iterative Reconstrained Low-Rank Representation via Weighted Nonconvex Regularizer
Iterative Reconstrained Low-Rank Representation via Weighted Nonconvex Regularizer Open
Benefiting from the joint consideration of geometric structures and low-rank constraint, graph low-rank representation (GLRR) method has led to the state-of-the-art results in many applications. However, it faces the limitations that the s…