Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks158 from public data
- 785
- 760
- 583
- 573
- Trusted Multi-View Classification With Dynamic Evidential Fusion558
The variational Dirichlet is introduced to characterize the distribution of the class probabilities, parameterized with evidence from different views and integrated with the Dempster-Shafer theory, which induces accurate uncertainty and accordingly endows the model with both reliability and robustness against possible noise or corruption.
- 552
- Consistent and Specific Multi-View Subspace Clustering450
A novel multi-view subspace clustering method (CSMSC), where consistency and specificity are jointly exploited for subspace representation learning, and forms the multi-View self-representation property using a shared consistent representation and a set of specific representations, which better fits the real-world datasets.
- Deep Partial Multi-View Learning338
A novel framework termed Cross Partial Multi-View Networks (CPM-Nets) is proposed, which aims to fully and flexibly take advantage of multiple partial views to provide completeness and versatility for multi-view representation and theoretically prove the versatility of the learned latent representations.
- 289
- 286
- Diagnosis of Coronavirus Disease 2019 (COVID-19) With Structured Latent Multi-View Representation Learning254
This study proposes to conduct the diagnosis of COVID-19 with a series of features extracted from CT images, and shows that the proposed method outperforms all comparison methods, and rather stable performances are observed when varying the number of training data.
- Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis and Multiple Cues Fusion252
A measure to evaluate the reliability of depth map, and use it to reduce the influence of poor depth map on saliency detection, and two saliency maps are integrated into a final saliency map through weighted-sum method according to their importance.
- 241
- 215
- Subspace clustering guided unsupervised feature selection209
Experimental results on benchmark datasets for unsupervised feature selection show that SCUFS outperforms the state-of-the-art UFS methods and can uncover the underlying multi-subspace structure of data.
- Provable Dynamic Fusion for Low-Quality Multimodal Data202
A novel multimodal fusion framework termed Quality-aware Multimodal Fusion (QMF) is proposed, which can improve the performance in terms of classification accuracy and model robustness and several uncertainty estimation solutions are naturally available to achieve robust multi-modal fusion.
- CPM-Nets: Cross Partial Multi-View Networks189
This work proposes a novel framework termed Cross Partial Multi-View Networks (CPM-Nets), which gives a formal definition of completeness and versatility for multi-view representation and theoretically proves the versatility of the latent representation learned from this algorithm.
- 188
- Multi-view subspace clustering with intactness-aware similarity185
A novel multi-view subspace clustering model that attempts to form an informative intactness-aware similarity based on the intact space learning technique is proposed and its superior performance over other state-of-the-art alternatives is revealed.
- 175
- Flexible Multi-View Representation Learning for Subspace Clustering174
This paper proposes to conduct subspace clustering based on Flexible Multi-view Representation (FMR) learning, which avoids using partial information for data reconstruction, and achieves superior clustering performance over other state-ofthe-art methods.
- Multi-label feature selection with missing labels172
This paper presents a novel multi-label feature selection model under the circumstance of missing labels, where the most discriminative features are selected and missing labels are recovered simultaneously.
- Multi-view Spectral Clustering Network156
To deeply cluster multi-view data, MvSCN incorporates the local invariance within every single view and the consistency across different views into a novel objective function, where theLocal invariance is defined by a deep metric learning network rather than the Euclidean distance adopted by traditional approaches.
- 153
- 150
- Tensorized Multi-view Subspace Representation Learning149
A novel algorithm termed as Tensorized Multi-view Subspace Representation Learning is established, which models elegantly the complementary information among different views, reduces redundancy of subspace representations, and then improves the accuracy of subsequent tasks.
- Multi-View Information-Bottleneck Representation Learning127
A novel and flexible unsupervised multi-view representation learning model termed Collaborative Multi-View Information Bottleneck Networks (CMIB-Nets), which comprehensively explores the common latent structure and the view-specific intrinsic information, and discards the superfluous information in the data significantly improving the generalization capability of the model.
- 122
- 122
- Latent Semantic Aware Multi-View Multi-Label Classification115
A novel approach for multi-view multi-label learning based on matrix factorization to exploit complementarity among different views and provides theoretical guarantee for the strict convexity for this method by properly setting parameters.
- Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data109
An early AD diagnosis framework via novel multi-modality latent space inducing ensemble SVM classifier is proposed, which first project the neuroimaging data from different modalities into a latent space, and then map the learned latent representations into the label space to learn multiple diversified classifiers.
- Trustworthy Long-Tailed Classification106
A Trustworthy Long-tailed Classification (TLC) method to jointly conduct classification and uncertainty estimation to identify hard samples in a multi-expert framework and a dynamic expert en-gagement to reduce the number of engaged experts for easy samples and achieve efficiency while maintaining promising performances.
- 105
- Platelets and diseases: signal transduction and advances in targeted therapy100
The structure, signaling pathways, biological functions, and therapeutic potential of platelets are explored, highlighting their roles in both physiological and pathological contexts.
- Incomplete multi-modal representation learning for Alzheimer’s disease diagnosis99
An Auto-Encoder based Multi-View missing data Completion framework (AEMVC) to learn common representations for AD diagnosis is proposed and experimental results achieved on Alzheimers Disease Neuroimaging Initiative datasets validate the effectiveness of the proposed method.
- Efficient registration of multi-view point sets by K-means clustering98
This paper casts the multi-view registration into a clustering problem, which can be solved by the extended K-means clustering algorithm, which can achieve the clustering as well as the multi-view registration by iterations.
- Nighttime low illumination image enhancement with single image using bright/dark channel prior98
A dual channel prior-based method for nighttime low illumination image enhancement with a single image, which builds upon two existing image priors: dark channel prior and bright channel prior is proposed.
- 96
- 93
- Fairness-guided Few-shot Prompting for Large Language Models87
This paper introduces a metric to evaluate the predictive bias of a fixed prompt against labels or a given attributes and proposes a novel search strategy based on the greedy search to identify the near-optimal prompt for improving the performance of in-context learning.
- Uncertainty-inspired open set learning for retinal anomaly identification87
UIOS provides a robust method for real-world screening of retinal anomalies and correctly predicts high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images.
- 72
- 71
- Co-regularized unsupervised feature selection70
Joint l2,1-norm co-regularization is imposed on multiple feature selection matrices to ensure that the selected features can both preserve data distribution and data reconstruction.
- Coupled Dictionary Learning for Unsupervised Feature Selection69
This work proposed a novel coupled analysis-synthesis dictionary learning method, which is free of generating labels, to solve the L2p-norm optimization problem and proved it can converge to a fixed point.
- Multi-view label embedding65
Experiments on benchmark databases show that MVLE outperforms the state-of-the-art LSDR algorithms in both multi-view settings and different multi-View learning strategies.
- 61
- Research on axial bearing capacity of rectangular concrete-filled steel tubular columns based on artificial neural networks61
Parametric study was conducted using ANN1 and ANN2 which indicates that effect law of basic parameters of columns on the axial bearing capacity of rectangular CFT columns differs from design codes, and provides convincing design reference to rectangular C FT columns.
- 58
- Multi-modal sequence learning for Alzheimer’s disease progression prediction with incomplete variable-length longitudinal data56
This study considers a flexible yet more challenging scenario in which individuals may suffer from the (arbitrary) modality-missing issue, as well as the number of individuals' historical visits and the length of target score trajectories being not prespecified.
- Multi-Layer Multi-View Classification for Alzheimer’s Disease Diagnosis56
A Multi-Layer Multi-View Classification (ML-MVC) approach, which regards the multi-view input as the first layer, and constructs a latent representation to explore the complex correlation between the features and class labels, and captures the high-order complementarity among different views.
- UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup54
This work proposes a simple yet practical framework, called uncertainty-aware mixup (UMIX), to mitigate the overfitting issue in over-parameterized models by reweighting the ''mixed'' samples according to the sample uncertainty.
- Calibrating Multimodal Learning52
This paper finds that the confidence estimated by current models could even increase when some modalities are corrupted, and proposes a novel regularization technique, i.e., Calibrating Multimodal Learning (CML) regularization, to calibrate the predictive confidence of previous methods.
- 51
- Predictive Dynamic Fusion49
A Predictive Dynamic Fusion framework for multimodal learning is proposed and theoretically derive the predictable Collaborative Belief (Co-Belief) with Mono- and Holo-Confidence, which provably reduces the upper bound of generalization error.
- FISH-MML: Fisher-HSIC Multi-View Metric Learning49
This work presents a simple yet effective model for multi-view metric learning, which aims to improve the classification of data with multiple views, e.g., multiple modalities or multiple types of features, based on Fisher discriminant analysis and Hilbert-Schmidt Independence Criteria.
- 48
- 45
- Unsupervised feature selection via Diversity-induced Self-representation45
This paper proposes a Diversity-induced Self-representation (DISR) based unsupervised feature selection method to effectively select the features with both representativeness and diversity, and introduces a novel diversity term, which adjusts the weights of selected features by incorporating the similarities between features.
- Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification44
An Uncertainty-induced Incomplete Multi-View Data Classification (UIMC) model is proposed to classify the incomplete multi-view data under a stable and reliable framework and establishes a state-of-the-art performance in terms of both performance and trustworthiness.
- Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning43
This paper presents a complete process, from data collection and construction to model training and overfitting elimination, for fine-tuning LLMs in vertical domain deployments, and reveals that incorporating reasoning processes during the fine-tuning of LLMs can effectively alleviate overfitting.
- 43
- Biomarkers of ageing of humans and non-human primates42
This Review discusses biomarkers of ageing and of ageing-associated physiological changes, at the cellular, tissue and organism levels in humans and non-human primates, highlighting their importance in assessing and intervening in the ageing process.
- 41
- SGU-Net: Shape-Guided Ultralight Network for Abdominal Image Segmentation41
The proposed SGU-Net includes an ultralight convolution that is able to implement double separable convolutions simultaneously and employs an additional adversarial shape-constraint to let the network learn shape representation of targets, which can significantly improve the segmentation accuracy for abdomen medical images using self-supervision.
- Safe Multi-View Deep Classification37
A Safe Multi-view Deep Classification (SMDC) method is proposed, which can guarantee that the classification performance does not deteriorate when fusing multiple views and theoretically proves that in the safe multi-view classification, adding data views will certainly not increase the empirical risk of classification.
- 37
- 31
- Fetal Alcohol Programming of Hypothalamic Proopiomelanocortin System by Epigenetic Mechanisms and Later Life Vulnerability to Stress31
It is demonstrated that the epigenetic programming of the POMC system by FAE was reversed in adulthood with the application of the inhibitors of DNA methylation or histone modifications, indicating that prenatal environmental influences such as alcohol exposure could epigenetically modulate POMC neuronal circuits and function to shape adult behavioral patterns.
- 30
- Infant Brain Development Prediction With Latent Partial Multi-View Representation Learning28
A novel model, latent partial multi-view representation learning, is established to intuitively explore complementary information from different time-points and handle the missing data issue in longitudinal studies simultaneously and validates the effectiveness of the proposed algorithm.
- Confidence-aware multi-modality learning for eye disease screening26
This study proposes a novel multi-modality evidential fusion pipeline for eye disease screening that provides a measure of confidence for each modality and elegantly integrates the multi-modality information using a multi-distribution fusion perspective.
- 25
- Towards Generalized and Efficient Metric Learning on Riemannian Manifold25
This paper makes an attempt to propose a generalized and efficient Riemannian manifold metric learning (RMML) method, which can be flexibly adopted to both SPD and Grassmann manifolds, and demonstrates the RMML performs favorably against its counterparts in terms of both accuracy and efficiency.
- $$\text {M}^2\text {Net}$$: Multi-modal Multi-channel Network for Overall Survival Time Prediction of Brain Tumor Patients24
An end-to-end OS time prediction model, Multi-modal Multi-channel Network, which first project the 3D MR volume onto 2D images in different directions, which reduces computational costs, while preserving important information and enabling pre-trained models to be transferred from other tasks.
- Shape-Preserving Object Depth Control for Stereoscopic Images24
Experimental results show that the proposed shape-preserving object depth control method can control object depth and preserve the shape of the object effectively without sensible background distortion.
- Weighted median guided filtering method for single image rain removal19
A weighted median guided filtering method for rain removal with a single image that is comparable to the state-of-the-art algorithms with low computation cost is presented.
- 19
- RED-Nets: Redistribution Networks for Multi-View Classification18
A novel multi-view classification model termed Redistribution Networks for Multi-View Classification (RED-Nets) is proposed, which is able to jointly explore consistency and diversity in a flexible manner and is more effective than the state-of-the-art methods.
- 18
- 16
- 16
- 16
- 16
- Beyond Similar and Dissimilar Relations : A Kernel Regression Formulation for Metric Learning15
The proposed RAML method formulates metric learning as a kernel regression problem, which can be efficiently optimized by the standard regression solvers and achieves favorable performance against the state-of-the-art methods.
- 15
- Multi-cue Augmented Face Clustering15
A new algorithm, Multi-cue Augmented Face Clustering (McAFC), which effectively incorporates the cues via graph-guided sparse subspace clustering technique, and demonstrates the improvements of the algorithm over the state-of-the-art methods.
- 14
- 13
- The Establishment of M13 Phage Clones Displayed#br#Epitope Recognized by BAC5 McAb12
In China, acute rheumatic carditis is an important etiology of valve prolapse, especially for anterior mitral leaflet prolapse, especially for anterior mitral leaflet prolapse.
- Skip \n: A Simple Method to Reduce Hallucination in Large Vision-Language Models11
A new perspective is proposed, suggesting that the inherent biases in LVLMs might be a key factor in hallucinations, and a simple method is proposed to effectively mitigate the hallucination of LVLMs by skipping the output of '\n'.
- 11
- A computer-aided system for linear production designs11
By using the multi-criteria and multi-constraint-level (MC 2 ) simplex method, a computer-aided system for identifying the optimal production systems and their corresponding optimal contingency plans for production is developed.
- SPL-MLL: Selecting Predictable Landmarks for Multi-label Learning10
This work proposes to select a small subset of labels as landmarks which are easy to predict according to input (predictable) and can well recover the other possible labels (representative) to ensure both the representativeness and predictableness for selected landmarks.
- 10
- Entropy-based active sparse subspace clustering10
A novel extension for SSC with active learning framework is proposed, in which the most informative pairwise constraints are selected to guide the SSC for accurate clustering results.
- Multi-modal Neuroimaging Data Fusion via Latent Space Learning for Alzheimer’s Disease Diagnosis10
This work proposes a novel AD diagnosis framework based on latent space learning with ensemble classifiers, by integrating the latent representation learning and ensemble of multiple diversified classifiers learning into a unified framework.
- Cortactin Facilitates Malignant Transformation of Dysplastic Cells in Gastric Cancer Development9
It is suggested that cortactin is a functional element of membrane dynamics, malignant changes, and exosome secretion in dysplastic cells, and solid gastric tumor formation associated with alteration of the tumor microenvironment.
- Trustworthy deep learning for encrypted traffic classification9
A novel traffic classification method based on trustworthy deep learning model that can effectively improve the reliability of encrypted traffic classification models by correcting the confidence of model output and has a good ability to identify misclassified samples compared with state-of-the-art methods.
- dugMatting: Decomposed-Uncertainty-Guided Matting8
A decomposed-uncertainty-guided matting (dugMatting) algorithm, which explores the explicitly decomposed uncertainties to efficiently and effectively improve the results.
- 8
- A flexible framework of adaptive method selection for image saliency detection8
An instance-aware method selection approach which aims to select a single method instead of aggregating the results of all candidate ones, which is more efficient and flexible to employ metric learning technique.
- 7
- 7
- Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model6
This work introduces a test-time prompt tuning paradigm that optimizes a learnable prompt, thereby compelling the model to exploit invariant features while disregarding decision shortcuts during the inference phase, and conducts comparative analysis of the proposed method against various approaches which validates the significant superiority.
- Selective Learning: Towards Robust Calibration with Dynamic Regularization6
DReg effectively fits the labels for in-distribution samples while applying regularization dynamically to samples beyond model capabilities (e.g., outliers), thereby obtaining a robust calibrated model especially on the samples beyond model capabilities.
- Generalized Multi-view Unsupervised Feature Selection6
A novel unsupervised feature selection method is proposed, termed as generalized Multi-View Unsupervised Feature Selection (gMUFS), to simultaneously explore the complementarity of multiple views, and complex correlation between cluster structure and selected features as well.
- Semi-Supervised Multi-view Multi-label Classification Based on Nonnegative Matrix Factorization6
This work proposes a novel semi-supervised multi-view multi-label classification method based on nonnegative matrix factorization (NMF), which explores the complementary information by adopting multi- view NMF, regularizes the learned labels of each view towards a common consensus labeling, and obtains the labels of the unlabeled data guided by supervised information.
- Robust Multi-label Feature Selection with Missing Labels6
This paper proposes a robust model that recovers the missing labels by a linear regression model and select the most discriminative feature subsets simultaneously and has superior performance over the state-of-the-art algorithms.
- Multi-view Representative and Informative Induced Active Learning6
A novel method is proposed, called Multi-view Representative and Informative-induced Active Learning (MRI-AL), which selects samples of both representativeness and informativeness with the help of complementarity of multiple views using subspace reconstruction with structure sparsity technique.
- Human Skin Detection via Semantic Constraint6
Different from traditional skin detection algorithms, the semantic constraint is introduced, which is based on the dependence between skin pixels and human body parts (skin pixels should be overlapped with body parts) to refine the detection.
- Attributed Subspace Clustering5
Experiments on several benchmark image datasets have demonstrated the effectiveness of ASC not only in terms of clustering accuracy achieved by the integrated representation, but also the diverse interpretation of data, which is beyond what current approaches can offer.
- Chinese Address Similarity Calculation Based on Auto Geological Level Tagging5
A framework for calculating the similarity of Chinese addresses is constructed, taking into account the hierarchical nature of addresses, and has achieved good results in practice for financial anti-fraud tasks.
- Infant brain development prediction with latent partial multi-view representation learning5
This work introduces a multi-view multi-task learning approach to dexterously explore complementary information from different time points and handle the missing data simultaneously, and establishes a novel model termed as Latent Partial Multi-view Representation Learning.
- Reweighted Mixup for Subpopulation Shift4
This work proposes a simple yet practical framework, called reweighted mixup (RMIX), to mitigate the overfitting issue in over-parameterized models by conducting importance weighting on the ''mixed'' samples by leveraging reweighting in mixup.
- 4
- Deep Distillation Metric Learning4
A novel deep distillation metric learning (DDML) for online teaching in the procedure of learning the distance metric is proposed, which employs model distillation to transfer the knowledge acquired by the larger model to the smaller model.
- 4
- Unsupervised Subspace Learning via Analysis Dictionary Learning4
Experiments show that the proposed unsupervised dimension reduction model outperforms the state-of-the-art methods.
- Discrete Cosine Wavelet Packet Transform and Its Application in Compressed Sensing for Speech Signal4
- A Theoretical Proof of Dynamic Multimodal Fusion Exacerbates Modality Greedy3
The Greedy risk in dynamic multimodal learning is explained from both theoretical and experimental perspectives, serving as a cautionary reminder for researchers when employing dynamic multimodal learning.
- 3
- 3
- 2
- Generalized Few-Shot Out-of-Distribution Detection2
A Knowledge Dynamic Embedding mechanism to adaptively modulate the guidance of general knowledge and dynamically aligns the output distributions of the OOD detection model to the general knowledge model based on the Generalized Belief (G-Belief) of GKM, thereby boosting the GS-balance.
- 2
- 2
- 1
- 1
- 1
- Similarity measure-based spectrum sensing algorithm under impulsive noise1
A new spectrum sensing algorithm to determine whether a signal exists under impulsive noise by only using the sampled data is proposed and can suppress the influence of impulsive noise, realize accurate signal detection and improve the reliability of the system with fewer samples.
- LOGARITHMIC SIMILARITY MEASURE BASED COOPERATIVE SPECTRUM SENSING UNDER IMPULSIVE NOISE1
A cooperative spectrum sensing (CSS) algorithm is developed to alleviate the problems of hidden terminals under impulsive noise environments, and the accuracy of CSS is noticeably improved compared with the “OR” rule CSS.
- Latent Subspace Representation for Multiclass Classification1
This paper proposes a Latent Subspace Representation for Multiclass Classification (LSRMC), and learns the projection, subspace representation and classifier in a unified model, and solves the problem efficiently by using Augmented Lagrangian Multiplier with Alternating Direction Minimization.
- Application of Non-uniform Sampling in Compressed Sensing for Speech Signal1
The theoretical analysis and simulation results show that non-uniform observation can directly apply compressed sensing to analog speech signal processing, and the corresponding reconstruction method effectively enriches the means of compressive perception reconstruction.
- Multi-view Label Space Dimension Reduction1
Experiments show that the proposed multi-view learning model outperforms the best single-view model and the majority voting method and the proposed LSDR model for multi-label classification.
- LEAF1
A joint learning objective function which is composed of the high-order representation mining term and the classifier training term that can both preserve category-specific information and discover the common structure between categories.
- 1
- 1
- 1
- 1
- –
- –
- –
- Semantic Equivariant Mixup–
Different from previous mixup variants, which tend to over-focus on the label-related information, the proposed method aims to preserve richer semantic information in the input with semantic-equivariance assumption, thereby improving the robustness of the model against distribution shifts.
- –
- –
- –
- LRA: an accelerated rough set framework based on local redundancy of attribute for feature selection–
- –
- Set to Set Visual Tracking–
Both qualitative and quantitative analyses on several challenging image sequences show that the proposed SSVT algorithm outperforms the state-of-the-art trackers.
- Advanced security analysis of a signature scheme with message recovery–
More general forgery attacks are described to show clearly how to obtain these attacks and it is interesting that they covers all the known attacks.
- –
- –
- –
- –
- –
- –
- –
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 2026-10-12. 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.