Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks137 from public data
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications1,202
The motivations, mathematical representations, and structures of most GAN algorithms are introduced in detail, and they are compared to compare their commonalities and differences.
- A Survey on Self-Supervised Learning: Algorithms, Applications, and Future Trends638
A detailed introduction to the motivations behind most SSL algorithms is provided and their commonalities and differences are compared, as well as representative applications of SSL in domains such as image processing, computer vision, and natural language processing.
- Feature Selection Based on Structured Sparsity: A Comprehensive Study335
This paper compares the differences and commonalities of these methods based on regression and regularization strategies, but also provides useful guidelines to practitioners working in related fields to guide them how to do feature selection.
- Fast Supervised Discrete Hashing272
This paper proposes a new learning-based hashing method called "fast supervised discrete hashing" (FSDH) based on “supervised discrete hashing” (SDH), which uses a very simple yet effective regression of the class labels of training examples to the corresponding hash code to accelerate the algorithm.
- Discriminant sparse neighborhood preserving embedding for face recognition264
DSNPE not only preserves the sparse reconstructive relationship of SNPE, but also sufficiently utilizes the global discriminant structures from the following two aspects: maximum margin criterion (MMC) is added into the objective function of DSNPE.
- Face recognition via Weighted Sparse Representation231
A locality Weighted Sparse Representation based Classification (WSRC) method is proposed, which utilizes both data locality and linearity; it can be regarded as extensions of SRC, but the coding is local.
- Using manifold embedding for assessing and predicting protein interactions from high-throughput experimental data227
A robust manifold embedding technique for assessing the reliability of interactions and predicting new interactions, which purely utilizes the topological information of PPI networks and can work on a sparse input protein interactome without requiring additional information types.
- 188
- Prediction of Protein-Protein Interactions from Protein Sequence Using Local Descriptors175
Given the complex nature of PPIs, the performance of the proposed sequence-based method is promising, and it can be a helpful supplement for PPIs prediction.
- A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning117
This article provides a comprehensive survey on supervised, semi-supervised, and unsupervised single image dehazing, and discusses the physical model, datasets, network modules, loss functions, and evaluation metrics that are commonly used.
- 115
- Large Margin Multi-Modal Multi-Task Feature Extraction for Image Classification106
A novel large margin multi- modal multi-task feature extraction (LM3FE) framework for handling multi-modal features for image classification that utilizes the complementarity of different modalities to further help reduce feature redundancy in each modality.
- Locality preserving discriminant projections for face and palmprint recognition101
The proposed LPDP combining manifold criterion and Fisher criterion has more discriminanting power, and is more suitable for recognition tasks than LPP, which considers only the local information for classification tasks.
- 100
- miRBaseConverter: an R/Bioconductor package for converting and retrieving miRNA name, accession, sequence and family information in different versions of miRBase98
The Bioconductor package miRBaseConverter and the Shiny-based web application are presented to provide a suite of functions for converting and retrieving miRNA name, accession, sequence, species, version and family information in different versions of miRBase.
- Supervised Discrete Hashing With Relaxation95
Compared with SDH, which uses the traditional zero-one matrix, SDHR utilizes the learned regression target matrix and, therefore, more accurately measures the classification error of the regression model and is more flexible.
- Binary Hashing for Approximate Nearest Neighbor Search on Big Data: A Survey93
This paper illustrates the development of binary hashing research by proposing an overall and clear classification of them, and conducts extensive experiments to compare the performance of these methods on five famous and public data sets.
- A Semi-Supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint92
A semi-supervised model for real-world nighttime dehazing that combines a pseudo-label-based retraining strategy and a local window-based brightness loss for semi-supervised training process is designed to suppress haze and glow while achieving realistic brightness.
- Automatic Modulation Classification for MIMO Systems via Deep Learning and Zero-Forcing Equalization92
A convolutional neural network (CNN) based zero-forcing (ZF) equalization AMC (CNN/ZF-AMC) method for MIMO systems is proposed and the impact of the imperfect CSI on the performance of this method is explored.
- 91
- Tumor classification by combining PNN classifier ensemble with neighborhood rough set based gene reduction90
Experiments showed that the proposed ensemble of probabilistic neural network (PNN) and neighborhood rough set model based gene reduction approach to tumor classification can obtain both high and stable classification performance, which is not too sensitive to the number of initially selected genes and competitive to most existing methods.
- Multi-Grained Attention Networks for Single Image Super-Resolution76
This paper proposes a unified approach called “multi-grained attention networks (MGAN)” which fully exploits the advantages of multi-scale and attention mechanisms in SR tasks and shows the superiority in terms of both accuracy and model size.
- 64
- Palmprint Recognition across Different Devices62
A robust method to calculate the palm width is proposed, which can be effectively used for scale normalization of palmprints, and results show that orientation coding based methods achieved promising recognition performance for PRADD.
- 55
- 44
- Highly Accurate Prediction of Protein-Protein Interactions via Incorporating Evolutionary Information and Physicochemical Characteristics44
A novel mixture of physicochemical and evolutionary-based feature extraction method for predicting PPIs using the newly developed discriminative vector machine (DVM) classifier, which is the first time that DVM model is applied to the field of bioinformatics.
- A Comprehensive Survey on Image Dehazing Based on Deep Learning43
A comprehensive survey on the recent proposed dehazing methods concludes the commonly used datasets, loss functions and evaluation metrics and group the existing researches into two major categories: supervised ID and unsupervised ID.
- R 2 SDH43
In R 2 SDH, correntropy is adopted to replace the least square regression (LSR) model in SDH for achieving better robustness, and rotation is integrated into the original zero-one label matrix used inSDH, as additional freedom to promote flexibility without sacrificing accuracy.
- 42
- Perceptually motivated morphological strategies for shape retrieval40
The proposed perceptually motivated morphological strategies (PMMS) are applied to improve the retrieval performances of a popular shape matching method named Inner-Distance Shape Contexts (IDSC), and then the Locally Constrained Diffusion Process (LCDP) method is exploited to further enhance the retrieval performance.
- 39
- Multi-step dimensionality reduction and semi-supervised graph-based tumor classification using gene expression data39
A semi-supervised graph-based method for tumor classification that can effectively improve the performance of tumor classification based on gene expression profiles is introduced.
- Hand shape recognition based on coherent distance shape contexts36
This paper creates a new hand image database containing 4000 grayscale left hand images of 200 subjects, on which CDSC has achieved the accurate identification rate of 99.60% for identification and the Equal Error Rate of 0.9% for verification, which are comparable with the state-of-the-art hand shape recognition methods.
- Newborn footprint recognition using orientation feature36
A novel online newborn personal authentication system based on footprint recognition that can capture digital footprint images with high quality and develop a preprocessing method for orientation and scale normalization.
- Illumination Controllable Dehazing Network based on Unsupervised Retinex Embedding34
A multi-output dehazing network by introducing illumination controllable ability, called IC-Dehazing, which can change the illumination intensity by adjusting the factor of the illumination controllable module, which is realized based on the interpretable Retinex model.
- 29
- 27
- 27
- Feedback Pyramid Attention Networks for Single Image Super-Resolution25
A novel feedback connection structure is developed to enhance low-level feature expression with high-level information and introduce a pyramid non-local structure to model global contextual information in different scales and improve the discriminative representation of the network.
- Fooling the Image Dehazing Models by First Order Gradient21
A group of attack methods based on first order gradient to verify the robustness of the existing dehazing algorithms are designed, which are predicted dehazed image attack, hazy layer mask attack, haze-free image attack and haze-preserved attack.
- 21
- 21
- Exploring the Coordination of Frequency and Attention in Masked Image Modeling19
This work proposes the Frequency & Attention-driven Masking and Throwing Strategy (FAMT), which can detect semantic patches and reduce the number of training patches to boost model performance and training efficiency simultaneously and introduces a patch throwing strategy based on the derived sampling weights to reduce the training cost.
- 19
- CFVNet: An End-to-End Cancelable Finger Vein Network for Recognition19
This work proposes an end-to-end cancelable finger vein network (CFVNet), which can be used to design an secure finger vein recognition system and integrates preprocessing and template protection into an integrated deep learning model.
- 19
- 17
- 17
- 17
- 16
- 16
- 15
- 15
- Improving Fast Adversarial Training via Self-Knowledge Guidance14
The Self-Knowledge Guided FAT is formed, leveraging naturally generated knowledge during training to enhance the adversarial robustness without compromising training efficiency, and extensive experiments demonstrate that the SKG-FAT improves the robustness and preserves competitive clean accuracy, outperforming the state-of theart methods.
- Noah: Reinforcement-Learning-Based Rate Limiter for Microservices in Large-Scale E-Commerce Services14
- 14
- 13
- 13
- 13
- 12
- 12
- 11
- Learning the Relation Between Similarity Loss and Clustering Loss in Self-Supervised Learning11
This paper attempts to leverage the similarity between two distinct images to boost representation in self-supervised learning, and analyzes the relation between similarity loss and feature-level cross-entropy loss.
- 11
- 11
- 11
- 10
- 10
- 9
- Backdooring Self-Supervised Contrastive Learning by Noisy Alignment9
Noisy Alignment is proposed, a DPCL method that explicitly suppresses noise components in poisoned images, achieving state-of-the-art performance compared to existing DPCLs, while maintaining clean-data accuracy and demonstrating robustness against common backdoor defenses.
- 9
- 9
- 9
- 9
- 9
- 8
- ColorVein: Colorful Cancelable Vein Biometrics7
An innovative cancelable vein biometric generation scheme, ColorVein, which allows users/administrators to define a controllable pseudo-random color space for grayscale vein images by editing the position, number, and color of hint points, thereby generating protected cancelable templates.
- 7
- 7
- 7
- An Efficient Cross-Modality Self-Calibrated Network for Hyperspectral and Multispectral Image Fusion7
- AlignVE: Visual Entailment Recognition Based on Alignment Relations7
A new architecture called AlignVE is proposed to solve the visual entailment problem with a relation interaction method that models the relation between the premise and hypothesis as an alignment matrix.
- 7
- 7
- 6
- 5
- 5
- 5
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 1
- 1
- 1
- The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perception1
The Diffusion-Based Nighttime Dehazing (DiffND) framework is introduced, which excels in both data synthesis and lighting reconstruction and proposes a restoration model that integrates a pre-trained diffusion model guided by a brightness perception network.
- 1
- 1
- 1
- 1
- Underwater Organism Color Enhancement via Color Code Decomposition, Adaptation and Interpolation1
Quantitative and visual evaluations on popular and challenging benchmark datasets demonstrate the superiority of ColorCode over existing methods in providing diverse, controllable, and color-realistic enhancement results.
- No Place to Hide: Dual Deep Interaction Channel Network for Fake News Detection based on Data Augmentation1
A novel framework for fake news detection from perspectives of semantic, emotion and data enhancement is proposed, which excavates the emotional evolution patterns of news participants during the propagation process and a dual deep interaction channel network of semantic and emotion is designed to obtain a more comprehensive and fine-grained news representation with the consideration of comments.
- 1
- AntNet: Deep Answer Understanding Network for Natural Reverse QA.1
Experimental results indicate that the proposed deep answer understanding network, called AntNet, for reverse QA is significantly better than existing methods and those modified from classical natural language processing (NLP) deep models.
- 1
- 1
- –
- –
- –
- –
- –
- –
- FVeinSyn: Synthetic Finger Vein Image Generator–
FVeinSyn explicitly decouples synthesis of vascular topology and imaging appearance to mitigate the limitations caused by insufficient training samples, such as inadequate identity diversity and restricted realism.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.