Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Dong YueSuggested from co-authorship
- Jian Jun YangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works154 from public data
- Lednet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation411
This paper presents LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation, which adopts a ResNet as backbone network to greatly reduce computation cost while maintaining higher segmentation accuracy.
- Lightweight Real-Time Semantic Segmentation Network With Efficient Transformer and CNN185
This work proposes a lightweight real-time semantic segmentation network called LETNet that combines a U-shaped CNN with Transformer effectively in a capsule embedding style to compensate for respective deficiencies.
- CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution164
This work proposes an efficient CNN-Transformer Cooperation Network (CTCNet) for face super-resolution tasks, which uses the multi-scale connected encoder-decoder architecture as the backbone and devise a novel Local-Global Feature Cooperation Module (LGCM) to promote the consistency of local facial detail and global facial structure restoration simultaneously.
- FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation154
This article proposes a Fast Bilateral Symmetrical Network (FBSNet), a symmetrical encoder-decoder structure with two branches, semantic information branch and spatial detail branch that can strike a good balance between accuracy and efficiency.
- MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation146
A novel lightweight network using a multi-scale context fusion (MSCFNet) scheme, which explores an asymmetric encoder-decoder architecture to alleviate the trade-off between accuracy, inference speed, and model size.
- 143
- Multi-scale deep context convolutional neural networks for semantic segmentation132
This paper designs a multi-scale deep context convolutional network (MDCCNet), which combines the feature maps from different levels of network in a holistic manner for semantic segmentation and demonstrates that the method outperforms or is comparable to state-of-the-art methods on PASCAL VOC 2012 and SIFTFlow semantic segmentations datasets.
- Feature Distillation Interaction Weighting Network for Lightweight Image Super-resolution122
This work proposes a lightweight yet efficient Feature Distillation Interaction Weighted Network (FDIWN), which utilizes a series of specially designed Feature Shuffle Weighted Groups as the backbone, and several novel mutual Wide-residual Distillation interaction Blocks form an FSWG.
- Chinese Image Captioning via Fuzzy Attention-based DenseNet-BiLSTM121
A fuzzy attention-based DenseNet-BiLSTM Chinese image captioning method that improves the problem of correspondence between image features and contextual information and achieves higher scores in objective quantitative evaluation indicators.
- Learning robust and discriminative low-rank representations for face recognition with occlusion114
This paper proposes a novel method by exploiting the low-rankness of both the data representation and each occlusion-induced error image simultaneously, by which the global structure of data together with the error images can be well captured.
- Adaptive deformable convolutional network94
This paper reformulates the deformable convolution and RoIpooling by reconsidering spatial-wise attention, channel-wise Attention and spatial-channel interdependency, to improve the single convolution’s ability to focus on pertinent image contents.
- Cross-Receptive Focused Inference Network for Lightweight Image Super-Resolution91
A novel Cross-receptive Field Guided Transformer is designed to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention.
- 85
- 82
- A Systematic Survey of Deep Learning-Based Single-Image Super-Resolution79
This survey gives an overview of DL-based SISR methods and group them according to their design targets and presents the reconstruction results of some classic SISR methods to intuitively know their performance.
- Regional deep learning model for visual tracking78
A regional deep learning tracker that observes the target by multiple sub-regions and each region is observed by a deep learning model, and devise a stable factor, modeled as a hidden variable of the Factorial Hidden Markov Model, to characterize the stability of these sub-models.
- Constructing multilayer locality-constrained matrix regression framework for noise robust face super-resolution58
An efficient multilayer locality-constrained matrix regression (MLCMR) framework to learn the representation of the input LR patch and meanwhile preserve the manifold of the original HR space and aims at reducing the inconsistency gap between different manifolds.
- Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition57
A feature set-based representation learning (FSRL) scheme to collaboratively represent the hierarchical features for more accurate recognition and the superiority of the presented algorithm to the other competitive CRFR approaches is verified.
- Discriminative histograms of local dominant orientation (D-HLDO) for biometric image feature extraction53
This paper presents a simple and robust method, namely discriminative histograms of local dominant orientation (D-HLDO), for biometric image feature extraction, applied to face, finger-knuckle-print and Palm biometrics and is examined using the AR, CMU PIE and FRGCv2.0 face image databases.
- Integration of multiple orientation and texture information for finger-knuckle-print verification51
A novel multiple orientation and texture information integration scheme is proposed in this paper that not only considers more orientations, but also introduces a multilevel image thresholding scheme to perform orientation coding on each Gabor filtering response.
- Cross-resolution face recognition with pose variations via multilayer locality-constrained structural orthogonal procrustes regression48
The proposed MLCSOPR not only learns the pose-robust discriminative representation features to reduce the resolution gap between the LR image space and the high-resolution (HR) one but also strengthens the consistency between theLR and HR image space.
- Efficient Image Super-Resolution With Feature Interaction Weighted Hybrid Network46
This work proposes a Feature Interaction Weighted Hybrid Network (FIWHN), which comprises a series of Wide-residual Distillation Interaction Block (WDIB) as the backbone, and incorporates a Transformer and explores a novel architecture to combine CNN and Transformer.
- 46
- HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation41
HAFormer is introduced, a model that combines the hierarchical features extraction ability of CNNs with the global dependency modeling capability of Transformers to tackle lightweight semantic segmentation challenges and achieves high performance with minimal computational overhead and compact model size.
- Collaborative representation based local discriminant projection for feature extraction41
Experimental results on ORL, AR and CMU PIE face databases validate the superiority of CRLDP over other state-of-the-art algorithms.
- 40
- A novel sparse representation based framework for face image super-resolution40
A new face image super-resolution framework using the sparse representation (SR) is presented, and the experimental results demonstrate that the proposed method can achieve competitive performance compared with other state-of-the-art methods.
- Fuzzy Linear Regression Discriminant Projection for Face Recognition38
The proposed algorithm FLRDP seeks to generate an efficient subspace for the LRC method and could effectively handle variations between facial images and demonstrates the superiority of the proposed method over other state-of-the-art algorithms.
- NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results37
This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images to establish a new and powerful benchmark for the task of removing raindrops under varying lighting and focus conditions.
- Review of Quaternion-Based Color Image Processing Methods37
Past methods are reviewed and categorized to indicate that the quaternion representation method is effective, and models and methods based on it have rapidly developed.
- 37
- NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results35
The 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results establishes a new benchmark for stereo image SR.
- JSPNet: Learning joint semantic & instance segmentation of point clouds via feature self-similarity and cross-task probability35
Experimental results on a large-scale 3D indoor point cloud dataset S3DIS and a part-segmentation dataset ShapeNet have demonstrated the superiority of the proposed JSPNet method over existing state-of-the-arts in both semantic and instance segmentation.
- Leaning compact and representative features for cross-modality person re-identification33
This paper presents a new loss function called Enumerate Angular Triplet (EAT) loss, motivated by the knowledge distillation, to narrow down the features between different modalities before feature embedding, and presents a novel Cross-Modality Knowledge Distillation (CMKD) loss.
- 32
- JDSR-GAN: Constructing an Efficient Joint Learning Network for Masked Face Super-Resolution30
This work considers both tasks simultaneously and construct an efficient joint learning network, called JDSR-GAN, for masked face super-resolution tasks, and incorporates the identity information and attention mechanism into the network for feasible correlated feature expression and informative feature learning.
- A fine-grained orthodontics segmentation model for 3D intraoral scan data29
This work focuses on deformed teeth segmentation and provides a fine-grained tooth segmentation dataset (3D-IOSSeg), and proposes a fast graph convolutional network for 3D tooth segmentation named Fast-TGCN, which can quickly and accurately segment teeth from the mouth with complex structures and outperforms other methods in various evaluation metrics.
- 29
- Cross Paradigm Representation and Alignment Transformer for Image Deraining28
This work proposes a novel Cross Paradigm Representation and Alignment Transformer, which aligns and interacts with features in a two-stage progressive manner, enabling adaptive guidance and complementarity, and introduces the Adaptive Alignment Frequency Module (AAFM), which reduces the information gap within and between paradigms.
- Survey on Deep Face Restoration: From Non-blind to Blind and Beyond26
The prevalent factors responsible for real-world LQ images and degradation techniques used to synthesize LQ images are examined and degradation techniques used to synthesize LQ images are introduced.
- Short-term Load Forecasting by Using Improved GEP and Abnormal Load Recognition25
Compared with the existing abnormal data detection algorithms, the algorithm proposed in this article have higher advantages in missing detection rate, false detection rate and precision rate, and STLF-IGEP_ALR is superior to other short-term load forecasting algorithms in terms of the convergence speed, MAE, MAPE, RSME, and R2.
- PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolution22
This letter proposes a novel Transformer-based parallax fusion module called Parallax Fusion Transformer (PFT), and adopted the Swin Transformer as the backbone for feature extraction and SR reconstruction to form a pure Transformer architecture called PFT-SSR.
- Adaptive linear discriminant regression classification for face recognition21
This paper proposes an adaptive linear discriminant regression classification algorithm (ALDRC) that makes use of different weights to characterize the different contributions of the training samples and utilizes such weighting information to calculate the between-class and the within-class reconstruction errors, and seeks to find an optimal projection matrix.
- Locality-Constrained Double Low-Rank Representation for Effective Face Hallucination21
Extensive experimental results indicate that the proposed locality-constrained double low-rank representation method outperforms some state-of-the-art algorithms in terms of both visual quantity and objective metrics.
- Bayesian sample steered discriminative regression for biometric image classification21
A novel regression based classification model, namely Bayesian sample steered discriminative regression (BSDR), which simultaneously exploits the sample class label and the sample appearance for linear mapping function learning by virtue of the Bayesian formula is proposed.
- Unsupervised domain adaptation based on cluster matching and Fisher criterion for image classification20
A novel method to generate an accurate pseudo-label for each target sample in a latent discriminative subspace by considering both domain distributions is proposed and incorporates cluster matching and the Fisher criterion into a united model and design an ADMM algorithm to effectively solve the proposed method.
- Multi-scale patch based representation feature learning for low-resolution face recognition20
The proposed MSPRFL approach first exploits multi-level information to learn more accurate resolution-robust representation features of each patch with the help of a training dataset, and tries to fuse the multi-scale outputs by learning scale weights via an ensemble optimization model.
- Lightweight Feature De-redundancy and Self-calibration Network for Efficient Image Super-resolution19
An efficient Feature De-redundancy and Self-calibration Super-resolution network (FDSCSR) is proposed to reduce the repetitive feature information extracted by the model and further enhance the efficiency of the model.
- Deep Context Convolutional Neural Networks for Semantic Segmentation18
This paper designs a multi-scale deep context convolutional network (MDCCNet), which combines the feature maps from different levels of network in a holistic manner for semantic segmentation and demonstrates that the method outperforms or is comparable to state-of-the-art methods on PASCAL VOC 2012 and SIFTFlow semantic segmentations datasets.
- 17
- 16
- Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation15
The degradation mechanism of the noisy image is explored and a lightweight Multiple Degradation and Reconstruction Network (MDRN) is proposed to progressively remove noise to enable MDRN to learn richer and more accurate features from heterogeneous models, which make it possible to reconstruct higher-quality denoised images under extreme conditions.
- Locality-regularized linear regression discriminant analysis for feature extraction15
A novel dimensionality reduction method called locality-regularized linear regression discriminant analysis (LLRDA) for feature extraction is proposed according to the decision rule of LLRC and seeks to generate a subspace that is discriminant for LLRC.
- 13
- OCTAMamba: A State-Space Model Approach for Precision OCTA Vasculature Segmentation13
OCTAMamba is a novel U-shaped network based on the Mamba architecture, designed to segment vasculature in OCTA accurately, and outperforms state-of-the-art methods, providing a new reference for efficient OCTA segmentation.
- Feature extraction based on graph discriminant embedding and its applications to face recognition13
This paper presents a novel algorithm called graph discriminant embedding (GDE) for feature extraction and recognition, which combines local information and label information of data points to construct two neighbor graphs, which help to pull the same-class samples nearer and nearer and repel the not-same- class samples farther and farther when they are projected onto a feature subspace.
- 12
- 12
- Semi-supervised Dual-Branch Network for image classification12
This paper proposes a novel Semi-supervised Dual-Branch Network (SDB-Net), in which the first branch is trained with labeled and unlabeled data, and the other is trainedWith the designed three kinds of losses, the proposed SDB- net can be efficiently trained.
- Parameterless reconstructive discriminant analysis for feature extraction12
This paper proposes a novel method called parameterless reconstructive discriminant analysis (PRDA), which cannot only fit LRC well but also has two important characteristics: the performance of RDA depends on the parameter k that requires manual turning, while the authors' is parameter-free, and it adaptively estimates the heterogeneous nearest classes for each sample to construct the inter-class reconstruction scatter.
- Local similarity preserving projections for face recognition12
This paper proposes a novel supervised subspace learning method called local similarity preserving projections (LSPP) for linear dimensionality reduction (DR), which seeks to project the original high-dimensional data into a subspace, which preserves the local neighborhood structure of the data in a certain sense.
- 10
- Robust low-resolution face recognition via low-rank representation and locality-constrained regression10
A low-rank representation and locality-constrained regression (LLRLCR) based method to learn occlusion-robust representations features for final face recognition tasks and the face labels can be predicted via a simple yet powerful sparse representation based classifier engine.
- Face image super-resolution with pose via nuclear norm regularized structural orthogonal Procrustes regression10
This work proposes a nuclear norm regularized structural orthogonal Procrustes regression (N2SOPR) approach to acquire pose-robust feature representations for face hallucination with pose to acquire near-frontal faces for recognition purpose.
- A Multi-Branch Feature Extraction Residual Network for Lightweight Image Super-Resolution9
This work proposes a straightforward and efficient method, the Multi-Branch Feature Extraction Residual Network (MFERN), to tackle lightweight image SR through the fusion of multi-information self-calibration and multi-attention information.
- 9
- 9
- “Like charges repulsion and opposite charges attraction” law based multilinear subspace analysis for face recognition9
A novel face recognition approach called non-specific variations based multi-subspace analysis (NVMSA), which serially utilizes NVDA criterion to learn multiple discriminant subspaces corresponding to different variations, is proposed.
- 8
- ReviveDiff: A Universal Diffusion Model for Restoring Images in Adverse Weather Conditions8
This work proposes a universal network architecture, dubbed “ReviveDiff”, which can address various degradations and restore images to their original quality by enhancing and restoring their details, and demonstrates that ReviveDiff outperforms the state-of-the-art methods both quantitatively and visually.
- 8
- Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism8
This paper proposes to use Generative Adversarial Networks based on a deformable convolution and attention mechanism to solve the problem of cross-view image synthesis and uses deformed convolution in the U-net network to improve the network's ability to extract features of objects at different scales.
- Scene Prior Filtering for Depth Super-Resolution7
A Scene Prior Filtering network, SPFNet, which utilizes the priors’ surface normal and semantic map from large-scale models and designs a One-to-one Prior Embedding that continuously embeds every single modal prior into depth using Mutual Guided Filtering, further alleviating texture interference while enhancing edge representations.
- Attention-Guided Multiscale Interaction Network for Face Super-Resolution7
An attention-guided multiscale interaction network (AMINet), which incorporates local and global feature interactions, as well as encoder–decoder phase feature interactions, which allows the free flow of multiscale features from within modules and between the encoder and decoder, which can promote the complementarity of different scale features to enhance FSR.
- S2AFormer: Strip Self-Attention for Efficient Vision Transformer7
S2AFormer is introduced, an efficient Vision Transformer architecture built around a novel Strip Self-Attention (SSA) mechanism that delivers substantial accuracy improvements together with superior inference speed and throughput across both GPU and non-GPU platforms.
- Towards end-to-end container code recognition7
This paper proposes a fast end-to-end method of automatic recognition of container code that fills the gap by locating the region and detecting characters as well as making the classification.
- Graph regularized Bayesian tensor factorization based on Kronecker-Decomposable dictionary7
A graph regularized Bayesian tensor factorization based on KDSDL model is proposed and the experiments on tensor data with complex outliers demonstrate the superiority of the proposed methods over the existing state-of-the-art methods.
- AgentPolyp: Accurate Polyp Segmentation via Image Enhancement Agent6
AgentPolyp is presented, a novel framework driven by an intelligent agent that integrates CLIP-based semantic guidance and dynamic image enhancement with a lightweight segmentation network, offering a deployable solution for endoscopic polyp analysis.
- MacFormer: Semantic Segmentation with Fine Object Boundaries6
A new semantic segmentation architecture, ``MacFormer'', which features two key components, using learnable agent tokens and a Mutual Agent Cross-Attention mechanism, which facilitates the bidirectional integration of features across encoder and decoder layers.
- Robust Face Recognition via Multi-Scale Patch-Based Matrix Regression6
This work proposes a multi-scale patch-based matrix regression scheme based on which the ensemble of multi- scale outputs can be achieved optimally and outperforms several state-of-the-art patch- based face recognition algorithms.
- Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration5
A Measurement-Constrained Sampling (MCS) approach that enables diverse LQ face reconstructions conditioned on different textual prompts and can generate prompt-aligned results and outperforms existing BFR methods is proposed.
- 5
- Graph-structure constraint and Schatten p-norm-based unsupervised domain adaptation for image classification5
A unified framework incorporating both the geometric and statistical characteristics by adopting the non-convex Schatten p-norm and graph Laplacian constraints to preserve global and local structure information and constructing marginal and conditional distribution minimization terms to reduce the distribution shifts is proposed.
- A Novel Function Mining Algorithm Based on Attribute Reduction and Improved Gene Expression Programming5
This paper presents a function mining algorithm for remote-sensing data by using gene expression programming and rough sets (FMRS-ARGEP) and shows that the proposed algorithm outperforms traditional algorithms in terms of the average running time, the number of condition attributes after reduction, the attribute reduction ratio, the average convergence speed, thenumber of convergences, and the ${R^{2}}$ value of the model.
- A novel biclustering of gene expression data based on hybrid BAFS-BSA algorithm5
By combining Binary Artificial Fish Swarm with Binary Simulated Annealing algorithms, the hybrid algorithm named BAFS-BSA-BIC was proposed, and its robustness and quality are better than these algorithms in searching optimal biclusters of co-expressed genes.
- Low-Rank Representation and Locality-Constrained Regression for Robust Low-Resolution Face Recognition5
A low-rank representation and locality-constrained regression (LLRLCR) based approach to learn the occlusion-robust discriminative representations features for low-resolution face recognition tasks.
- 4
- Cycle mapping with adversarial event classification network for fake news detection4
A novel FND approach, called Cycle Mapping and Adversarial Event Classification Network (CMAECN) is proposed, which shows superior performance compared to the state-of-the-art multi-modal FND methods.
- Dual-aligned unsupervised domain adaptation with graph convolutional networks4
Extensive empirical evaluation on three real-world datasets shows that DUDA-GCN can perform better than state-of-the-art related domain adaptation methods.
- Robust Facial Image Super-Resolution by Kernel Locality-Constrained Coupled-Layer Regression4
This research presents a new super-resolution method for facial image via representation learning scheme that addresses the key problem for the super- resolution of facial image: high-resolution face recognition.
- Nuclear norm regularized coding with local position-patch and nonlocal similarity for face hallucination4
This paper proposes to directly use the image matrix based regression model for combination coefficients computation to preserve the essential structural information of the input patch matrix to improve the hallucination performance.
- RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation3
This paper revisits cross-modal fusion from the perspective of modality reliability and proposes a novel framework termed the Reliability-aware Self-Gated State Space Model (RSGMamba), which explicitly models modality reliability and dynamically regulates cross-modal interactions through a self-gating mechanism.
- Learning Dual-Domain Multi-Scale Representations for Single Image Deraining3
This work proposes a novel Dual-Domain Multi-Scale Representation Network (DMSR), which exploits joint multi-scale representations from both external and internal domains in parallel while leveraging the strengths of both spatial and frequency domains to capture more comprehensive properties.
- 3
- 3
- MFPNet: A Multi-scale Feature Propagation Network for Lightweight Semantic Segmentation3
A novel lightweight segmentation architecture, called Multi-scale Feature Propagation Network (MFPNet), is proposed to address the dilemma of limited feature representation capability and the lack of feature guidance during the decoding process.
- 3
- Local and global aligned spatiotemporal attention network for video-based person re-identification3
Experimental results on three video pedestrian datasets verify the effectiveness of the proposed local and global aligned spatiotemporal attention network.
- Structure-constrained discriminative dictionary learning based on Schatten p-norm for face recognition3
A novel model of structure-constrained discriminative dictionary learning based on the Schatten p-norm (SDDLSp), in which a weighted representation regularization term is constructed to generate a coefficient matrix with a class-wise block-diagonal structure, performs well in face recognition problems, particularly with training and testing images that are both polluted by large noises.
- A Novel Nonlocal Low Rank Technique for Fabric Defect Detection3
This work proposes a simple yet effective method, namely nonlocal low rank approximation (NLRA), for fabric defect detection, and results prove the validity and feasibility of the proposed NLRA algorithm.
- 3
- 3
- 3
- 2
- SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation2
Strip Cross-Attention (SCASeg), an innovative decoder head specifically designed for semantic segmentation, is proposed and a Cross-Layer Block (CLB) that integrates hierarchical feature maps from various encoder and decoder stages to form a unified representation for Keys and Values is introduced.
- Multi-Order Matching Network for Alignment-Free Depth Super-Resolution2
The Multi-Order Matching Network (MOMNet) is proposed, a novel alignment-free framework that adaptively retrieves and selects the most relevant information from misaligned RGB information consistent with depth across multi-order feature spaces.
- 2
- 2
- Unsupervised visual domain adaptation via discriminative dictionary evolution2
A Discriminative Dictionary Evolution (DDE) approach to seek discriminative features robust to domain shift and produces domain-invariant representations for cross-domain visual recognition meanwhile promotes the discriminativeness of the dictionary.
- Locality-constrained feature space learning for cross-resolution sketch-photo face recognition2
The proposed LCFSL approach not only build bridge to associate cross-domain face images, but also can learn resolution robust representation features for cross-resolution sketch-photo face recognition purpose.
- Nuclear Norm Regularized Structural Orthogonal Procrustes Regression for Face Hallucination with Pose.2
A nuclear norm regularized structural orthogonal Procrustes regression (N2SOPR) method to learn pose-robust feature representations for efficient face hallucination and results indicate that this proposed method can produce more reasonable near frontal face images for recognition purpose.
- 2
- Locality-Constrained Iterative Matrix Regression for Robust Face Hallucination2
A locality-constrained iterative matrix regression model for face hallucination task and use the alternating direction method of multipliers to solve it, showing the superiority of the proposed method over some state-of-the-art algorithms.
- 2
- 2
- Matrix Based Regression with Local Position-Patch and Nonlocal Similarity for Face Hallucination2
Experiments conducted on the FERET face dataset indicate that the matrix based regression model directly uses for combination coefficients computation could outperform other state-of-the-art algorithms in terms of both vision and quantity.
- Weight Competitive Coding for Finger-Knuckle-Print Verification2
A new Weighted Competitive coding (W-CompCode) scheme for effective feature matching based on Finger-knuckle-print based on Gabor filter response variations at each location is proposed.
- Sparse Representation Based Face Image Super-Resolution2
A new face image super-resolution method using the sparse representation, which first seeks a sparse representation for each low-resolution input, and then the representation coefficients are directly used to generate the corresponding high-resolution output.
- 1
- 1
- 1
- 1
- MambaMIC: An Efficient Baseline for Microscopic Image Classification with State Space Models1
A Local-Global dual-branch aggregation module: the MambaMIC Block, designed to effectively capture and fuse local connectivity and global dependencies and a Feature Modulation Interaction Aggregation Module for deep feature interaction and key feature re-localization.
- A PDE-Based Image Dehazing Method via Atmospheric Scattering Theory1
A novel partial differential equation framework for single-image dehazing is presented by integrating the atmospheric scattering model with nonlocal regularization and dark channel prior by integrating the atmospheric scattering model with nonlocal regularization and dark channel prior.
- 1
- A Decoder Structure Guided CNN‐Transformer Network for face super‐resolution1
A novel Decoder Structure Guided CNN‐Transformer Network (DCTNet) is introduced, which utilises the newly proposed Global‐Local Feature Extraction Unit (GLFEU) for effective embedding to recover detailed facial structures from low‐quality images.
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- CSW-AL: A category-scaling weight schema for imbalanced multi-domain active learning–
This work introduces a comprehensive framework featuring a dynamic category-scaling weight mechanism that hierarchically addresses imbalance at the sample and domain levels, and builds a progressively refined "Ideal Domain" through the adaptive integration of well-performing domains.
- –
- –
- RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement–
RPBA-Net is proposed, an interpretable residual pyramid bilateral affine network for RAW-domain ISP enhancement that surpasses representative RAW-to-sRGB methods and achieves state-of-the-art performance in reconstruction fidelity and perceptual quality, while maintaining low model complexity and strong deployment potential for mobile and embedded platforms.
- –
- –
- Traffic Image Restoration under Adverse Weather via Frequency-Aware Mamba–
Frequency-Aware Mamba is proposed, a novel framework that integrates frequency guidance with sequence modeling for efficient image restoration and a novel Adaptive Frequency Scanning Mechanism for the Mamba, which enables the Mamba to achieve frequency-domain scanning across distinct subgraphs, thereby fully leveraging the texture distribution characteristics inherent in subgraph structures.
- Low-tubal-rank tensor factorization on constant curvature Riemann manifold with mixture of Gaussians–
- Dual attention and part drop network for person reidentification–
A dual attention and part drop network (DAPD-Net) for person ReID enables the deep neural network to focus on the pedestrian in the foreground of a given image and weakens background perturbance and can speed up learning and improve network performance.
- –
- Quadratic Discriminant Analysis Metric Learning Based on Feature Augmentation for Person Re-Identification–
Feature augmentation is used to enhance the inherent properties of each camera to ensure the generalization ability of the camera by ensuring the feature of changes within each camera is taken into consideration and the final discriminative ability is improved.
- Face Hallucination Using Locality Preserving Canonical Correlation Analysis.–
A new face hallucination approach based on locality preserving canonical correlation analysis, which is referred to as LPCCA-SR, which utilizes principal component analysis to reduce the dimensions of HR and LR face images and super-resolves the input LR face images by global face reconstruction and residual compensation.
- Fractional Sparse Representation Based Classification and Multi-view Extension for Face Recognition.–
- Fuzzy Bilinear Latent Canonical Correlation Projection for Feature Learning–
A fuzzy bilinear canonical correlation projection (FBCCP) approach that not only considers two-dimensional spatial structure of images, but also membership degree of practical observation belonging to different classes at the same time is proposed.
- Joint Subspace and Dictionary Learning with Dynamic Training Set for Cross Domain Image Classification–
The proposed sparse representation based domain adaptation approach to tackle the cross-domain image classification problem aims to alleviate the distribution discrepancy and preserve the discriminative information from source domain, which is achieved by jointly learning a common subspace and a discrim inative dictionary.
- A Method of Pedestrian Re-identification Based on Multiple Saliency Features–
The proposed method of pedestrian re-identification based on multiple salient features based on the multi-layer cellular automata has better performance on CAVIAR4REID and iLIDS databases than the existing algorithms.
- Robust Face Hallucination via Locality-Constrained Nuclear Norm Regularized Regression–
A locality-constrained nuclear norm regularized regression model for face hallucination task and use the alternating direction method of multipliers to solve it and experiments show that LCNNR outperforms some state-of-the-art algorithms.
- –
- Binary code learning via optimal class representations–
It is shown that, by mapping images onto the optimal representation of their corresponding classes, the proposed method outperforms several other state-of-the-art supervised hashing methods in image retrieval on three large-scale datasets.
- Big Data Processing With Application to Image Super-Resolution–
Experiments conducted on the FERET face dataset indicate that the proposed novel matrix based regression model could outperform other state-of- the-art algorithms in terms of both vision and quantity.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.