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
- Wanqing LiSuggested from co-authorship
- Zhanjie SongSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works231 from public data
- Late Fusion Incomplete Multi-View Clustering374
This work proposes Late Fusion Incomplete Multi-view Clustering (LF-IMVC) which effectively and efficiently integrates the incomplete clustering matrices generated by incomplete views and develops a three-step iterative algorithm to solve the resultant optimization problem with linear computational complexity and theoretically prove its convergence.
- 339
- 319
- 315
- 295
- RGB-D-based action recognition datasets: A survey291
A comprehensive review of the most commonly used action recognition related RGB-D video datasets, including 27 single-view datasets, 10 multi- view datasets, and 7 multi-person datasets, resulting in a number of recommendations for collection of new datasets and use of evaluation protocols.
- 289
- Multi-view Clustering via Late Fusion Alignment Maximization257
This paper theoretically uncovers the connection between existing k-means clustering and the alignment between base partitions and consensus partition and proposes a simple but effective multi-view algorithm termed MVC-LFA, which proposes to maximally align the consensus partition with the weighted base partitions.
- CGD: Multi-View Clustering via Cross-View Graph Diffusion231
The proposed CGD takes the traditional predefined graph matrices of different views as input, and learns an improved graph for each single view via an iterative cross diffusion process by capturing the underlying manifold geometry structure of original data points, and leveraging the complementary information among multiple graphs.
- A network traffic forecasting method based on SA optimized ARIMA–BP neural network221
A network traffic prediction method based on SA (Simulated Annealing) optimized ARIMA, non-linear model BPNN and optimization algorithm SA can fully realize the potential of mining linear and non- linear laws of historical network traffic data, hence improving the prediction accuracy.
- GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering218
The consensus data presentation from multiple views is obtained via cross-sample and cross-view feature aggregation, which fully explores the complementary of similar samples, and the consensus representation and the view-specific representation are aligned by the structure-guided contrastive learning module.
- 218
- 198
- Unsupervised feature selection via multiple graph fusion and feature weight learning191
This paper introduces a novel and effective unsupervised feature selection method via multiple graph fusion and feature weight learning (MGF^2WL) to address these issues, and develops a graph fusion term to fuse multiple predefined similarity graphs for learning a unified similarity graph.
- Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks184
The image-based representations enable the existing ConvNet models trained on image data without training a large number of parameters from scratch, and achieve the state-of-art results on three large datasets, namely, the large-scale continuous gesture recognition dataset.
- 162
- Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks157
A new representation, namely, Scene Flow to Action Map (SFAM), that describes several long term spatio-temporal dynamics for action recognition from RGB-D data and takes better advantage of the trained ConvNets models over ImageNet.
- Unsupervised feature selection via latent representation learning and manifold regularization144
A robust unsupervised feature selection method which embeds the latent representation learning into feature selection and is carried out in the learned latent representation space which is more robust to noises.
- Robust unsupervised feature selection via dual self-representation and manifold regularization138
Experimental results on ten real-world data sets demonstrate that the proposed method can effectively identify important features, outperforming many state-of-the-art unsupervised feature selection methods in terms of clustering accuracy (ACC) and normalized mutual information (NMI).
- 132
- Multispectral Object Detection via Cross-Modal Conflict-Aware Learning131
This paper develops a two-stream one-stage detector based on CALNet for multispectral object detection and demonstrates that the approach considerably outperforms existing methods in resolving the cross-modal semantic conflict issue and achieving state-of-the-art accuracy in detection results.
- 119
- ConvNets-Based Action Recognition from Depth Maps through Virtual Cameras and Pseudocoloring112
Through transferring learning the models originally trained over ImageNet for image classification, the three ConvNets are trained independently on the color-coded DMMs constructed in three orthogonal planes, achieving state-of-the-art results on these datasets.
- Consensus learning guided multi-view unsupervised feature selection107
A consensus learning guided multi-view unsupervised feature selection method, which embeds multi-View feature selection into a non-negative matrix factorization based clustering with sparse constrain.
- Beyond Covariance: Feature Representation with Nonlinear Kernel Matrices106
This paper proposes an open framework to use the kernel matrix over feature dimensions as a generic representation and discusses its properties and advantages, which significantly elevates covariance representation to the unlimited opportunities provided by this new representation.
- 102
- Large-scale Isolated Gesture Recognition using Convolutional Neural Networks100
A convolutional Neural networks (ConvNets) based method is developed for gesture recognition and evaluated on the Large-scale Isolated Gesture Recognition at the ChaLearn Looking at People (LAP) challenge 2016.
- Defocus map estimation from a single image via spectrum contrast95
The proposed method takes into consideration not only the affect of light refraction but also the blur texture of an image, and is more reliable in defocus map estimation compared to various state-of-the-art methods.
- 94
- Boundary uncertainty aware network for automated polyp segmentation89
A novel boundary uncertainty aware network (BUNet) is proposed for precise and robust colorectal polyp segmentation and is superior to thirteen competing methods in terms of both effectiveness and generalization ability.
- Efficient and Effective Incomplete Multi-View Clustering89
The proposed Efficient and Effective Incomplete Multi-view Clustering (EE-IMVC) algorithm proposes to impute each incomplete base matrix generated by incomplete views with a learned consensus clustering matrix to solve the resultant optimization problem with linear computational complexity and theoretically prove its convergence.
- 88
- Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models85
Comprehensive experimental evaluations demonstrate that MemVR significantly mitigates hallucination across various MLLMs and excels in general benchmarks without incurring additional time overhead.
- Robust graph regularized unsupervised feature selection85
This work proposes a unified UFS framework via feature self-representation and robust graph regularization, with the aim at reducing the sensitivity to outliers from the following two aspects: an l2, 1-norm is used to characterize the feature representation residual matrix and an l1-norm based graph Laplacian regularization term is adopted to preserve the local geometric structure of data.
- 84
- 79
- Cross-View Local Structure Preserved Diversity and Consensus Learning for Multi-View Unsupervised Feature Selection75
This paper proposes a cross-view local structure preserved diversity and consensus semantic learning model for MV-UFS, termed CRV-DCL, and carefully design an efficient algorithm with convergence guarantee to solve the resultant optimization problem.
- 71
- 67
- 65
- 65
- 63
- Multi-view subspace clustering via adaptive graph learning and late fusion alignment63
This work proposes a multi-view subspace clustering method via adaptive graph learning and late fusion alignment (AGLLFA), where for each view, AGLLFA learns an affinity graph adaptively to capture the similarity relationship among samples.
- Depth recovery and refinement from a single image using defocus cues63
This method builds on the universal imaging principle: only scene at the focus distance will converge to a single sharp point on imaging sensor but other scene will yield different blur effects varying with its distance from the camera lens.
- 60
- Sample-Level Cross-View Similarity Learning for Incomplete Multi-View Clustering58
A Sample-level Cross-view Similarity Learning (SCSL) method for Incomplete Multi-view Clustering that simultaneously construct a complete similarity matrix across views based on the inter-view sample relationship and the intra-view sample relationship and a simultaneously learning consensus representation ensures the validity of the projection.
- 58
- Pixel-Superpixel Contrastive Learning and Pseudo-Label Correction for Hyperspectral Image Clustering52
A pixel–superpixel contrastive learning and pseudo-label correction (PSCPC) method for the HSI clustering that aligns the clustering pseudo-labels of pixels and superpixels and improves the generalization ability of the model.
- Multi-Level Confidence Learning for Trustworthy Multimodal Classification52
A feature confidence learning mechanism to suppress some redundant features, as well as enhancing the expression of discriminative feature dimensions in each modality, and the first work which integrates both feature and label-level confidence learning for multimodal classification is proposed.
- 50
- 50
- Object Detection in Hyperspectral Image via Unified Spectral–Spatial Feature Aggregation49
This study presents a novel spectral–spatial aggregation (S2ADet) object detector that effectively harnesses the rich spectral and spatial complementary information inherent in the HSI, and proposes a feature aggregation two-stream network for interacting spectral-spatial features.
- Online human action recognition based on incremental learning of weighted covariance descriptors49
An effective framework of such an approach to online action recognition from a stream of noisy skeleton data, using a weighted covariance descriptor as a means to accumulate information is presented.
- 48
- 48
- Graph regularized spatial–spectral subspace clustering for hyperspectral band selection47
A graph regularized spatial-spectral subspace clustering method for hyperspectral band selection, which adopts superpixel segmentation to preserve the spatial information of HSIs by segmenting their first principal component into diverse homogeneous regions, and which can mitigate the effect of noise on the band selection.
- Bipartite Graph-based Discriminative Feature Learning for Multi-View Clustering44
Bipartite graph-based discriminative feature learning for multi-view clustering is proposed, which combines bipartitegraph learning and discriminatives feature learning to a unified framework and achieves better or comparable clustering performance than the results of state-of-the-art methods.
- 42
- 42
- Saliency detection via affinity graph learning and weighted manifold ranking42
Comprehensive evaluations on three challenge datasets indicate that the proposed bottom-up saliency detection approach by affinity graph learning and weighted manifold ranking universally surpasses other unsupervised graph based saliency Detection methods.
- 38
- 38
- 37
- White blood cell classification via a discriminative region detection assisted feature aggregation network37
A deep neural network for WBC classification via discriminative region detection assisted feature aggregation (DRFA-Net), which can accurately locate the WBC area to boost final classification performance and can obtain higher accuracies when compared with other state-of-the-art WBC Classification methods.
- Speckle noise reduction for optical coherence tomography images via non-local weighted group low-rank representation37
Both qualitative and quantitative experimental results on real OCT images show the superior performance of the WGLRR model compared with other state-of-the-art speckle removal techniques.
- Predicting miRNA-disease association via graph attention learning and multiplex adaptive modality fusion36
MAMFGAT utilizes GAT as the main structure for feature aggregation and incorporates a multi-modal adaptive fusion module to extract features from three interconnected networks: the miRNA-disease association network, the miRNA similarity network, and the disease similarity network.
- Hyperspectral Band Selection via Spatial-Spectral Weighted Region-wise Multiple Graph Fusion-Based Spectral Clustering36
A hyperspectral band selection method via spatial-spectral weighted region-wise multiple graph fusion-based spectral clustering, referred to as RMGF briefly, to validate the superiority of the proposed method when compared with other state-of-the-art ones.
- Unsupervised feature selection via adaptive hypergraph regularized latent representation learning36
This work proposes a robust unsupervised feature selection method which embeds the latent representation learning into feature selection in the learned latent representation space which is more robust to noises.
- Gene selection for microarray data classification via adaptive hypergraph embedded dictionary learning34
This paper introduces a computational gene selection model for microarray data classification via adaptive hypergraph embedded dictionary learning (AHEDL), and demonstrates that AHEDL outperforms other state-of-the-art methods in terms of micro array data classification.
- 34
- DPNET: Dynamic Poly-attention Network for Trustworthy Multi-modal Classification33
A novel Dynamic Poly-attention Network (DPNET) is proposed for trustworthy multi-modal classification and achieves competitive performance compared to other state-of-the-art ones.
- No-reference stereoscopic image quality evaluator with segmented monocular features and perceptual binocular features33
A novel NR SIQA model is proposed by the introduction of the meaningful superpixel visual patches and the significant binocular perception models that obtains a good consistency with the subjective scores, and has more reliable performance than previous works in terms of prediction accuracy and generalization capability.
- Combining ConvNets with hand-crafted features for action recognition based on an HMM-SVM classifier33
This paper proposes a new framework for RGB-D-based action recognition that takes advantages of hand-designed features from skeleton data and deeply learned features from depth maps, and exploits effectively both the local and global temporal information.
- Gene selection for microarray data classification via subspace learning and manifold regularization33
An effective gene selection method is proposed to select the best subset of genes for microarray data with the irrelevant and redundant genes removed and this method performs better when compared with other state-of-the-art methods in terms of microarray data classification.
- 32
- Tensor-Based Multi-View Block-Diagonal Structure Diffusion for Clustering Incomplete Multi-View Data32
- Drug-Target Interaction Prediction via Dual Laplacian Graph Regularized Matrix Completion32
This work proposes an effective computational model of dual Laplacian graph regularized matrix completion, referred to as DLGRMC, to infer the unknown drug-target interactions and develops an alternative iterative strategy to solve the constrained matrix completion problem based on Augmented Lagrange Multiplier algorithm.
- 31
- 29
- MS-Former: Memory-Supported Transformer for Weakly Supervised Change Detection With Patch-Level Annotations29
A memory-supported transformer (MS-Former), a novel framework consisting of a bi-directional attention block (BAB) and a patch-level supervision scheme (PSS) tailored for weakly supervised CD with patch-level annotations, which improves the performance of fully supervised change detection methods.
- R²MRF: Defocus Blur Detection via Recurrently Refining Multi-Scale Residual Features29
A deep neural network which Recurrently Refines Multi-scale Residual Features (R2MRF) for defocus blur detection consistently and significantly outperforms the competitors in terms of both efficiency and accuracy.
- Dual graph regularized compact feature representation for unsupervised feature selection29
An efficient optimization algorithm based on Alternating Direction Method of Multipliers is developed to solve the proposed optimization problem and experiments on various types of real world datasets are conducted to demonstrate the effectiveness of the proposed method.
- 28
- 27
- 26
- Dual Laplacian regularized matrix completion for microRNA-disease associations prediction26
A matrix completion model with dual Laplacian regularization (DLRMC) is introduced to infer unknown miRNA-disease associations in heterogeneous omics data and significantly outperform a variety of previous methods.
- An effective edge-preserving smoothing method for image manipulation26
The method provides an unified framework to regularize the edge and texture pixels in the optimization so that geometric edges representing image structures can be well retained and fine edges of texture regions are removed or suppressed.
- 25
- 24
- 24
- A Large Scale RGB-D Dataset for Action Recognition24
Four state-of-the-art algorithms are evaluated on the large combined dataset and the results have verified the limitations of current algorithms and the effectiveness of the large dataset.
- 23
- Identification of encrypted and malicious network traffic based on one-dimensional convolutional neural network23
A convolutional neural network model: One-dimensional convolutional neural network with hexadecimal data (HexCNN-1D) that combines normalized processing and attention mechanisms that can identify most categories of network traffic including encrypted and malicious traffic data.
- 22
- 21
- Reliable Attribute-missing Multi-view Clustering with Instance-level and feature-level Cooperative Imputation21
The proposed RAM-MVC method outperforms nine baseline methods, as evidenced by real-world experiments using single-cell multi-view data and a reliable imputation guidance module that distinguishes between real and technical attribute-missing events, enabling discriminative imputation.
- 21
- Diversity and consistency learning guided spectral embedding for multi-view clustering21
This work proposes a novel multi-view clustering method (DCMSC) by constraining diversity and consistency in both the learned clustering label matrix and data space, which suppresses the effect of noises and decreases redundant information.
- 20
- 20
- 19
- Perceptual objective quality assessment of stereoscopic stitched images19
A new perceptual objective stereoscopic stitched image quality assessment (S-SIQA) method by considering different distortion types in the existing stitching methods, including color distortion, ghost distortion, structure distortion(shape distortion, information loss), and disparity distortion.
- HSTrans: Homogeneous substructures transformer for predicting frequencies of drug-side effects17
HSTrans is presented, a novel approach that treats drugs and SEs as sets of substructures, leveraging a transformer encoder for unified substructure embedding and incorporating an interaction module for association capture and outperforms other state-of-the-art approaches.
- 17
- 16
- 16
- 16
- Heterogeneous Graph Guided Contrastive Learning for Spatially Resolved Transcriptomics Data15
A heterogeneous Graph guided Contrastive Learning (stGCL) for aggregating spatial transcriptomics data is constructed, guided by the inherent heterogeneity of cellular molecules by dynamically coordinating triple-level node attributes through comparative learning loss distributed across view domains, thus maintaining view independence during the aggregation process.
- Multi-level Graph Subspace Contrastive Learning for Hyperspectral Image Clustering15
A multi-level graph subspace contrastive learning (MLGSC) for HSI clustering is proposed, which significantly outperforms the current state-of-the-art clustering methods.
- 15
- 14
- 14
- 14
- 14
- 14
- 14
- 13
- 13
- Efficient Multiple Kernel Clustering via Spectral Perturbation12
The proposed MKC method recovers the optimal clustering partition from base partitions by maximizing the eigen gaps to approximate the perturbation errors, and an equivalent optimization objective function is introduced to obtain base partitions.
- Computer-aided Linear Algebra Course on Jupyter-Python Notebook for Engineering Undergraduates12
A new form of computer-aided linear algebra course with the application of a set of Python computer programs implemented on the Jupyter notebooks platform is introduced, and the development of innovative teaching methodologies for this course are improved.
- Salient object detection using color spatial distribution and minimum spanning tree weight12
This paper uses a segmentation algorithm to decompose an image into superpixel-level elements, then uses these elements as nodes to construct a minimum spanning tree (MST), each connected edge weight is the mean color difference between two nodes.
- 11
- Trusted Mamba Contrastive Network for Multi-View Clustering11
A new Trusted Mamba Fusion Network (TMFN) is presented, which achieves a trusted fusion of multi-view data through a selective mechanism and aligns the fused representation and the view-specific representation using the Average-similarity Contrastive Learning (AsCL) module.
- 11
- 11
- 10
- 10
- Joint dictionary and graph learning for unsupervised feature selection10
This paper proposes a model to integrate dictionary learning, similarity graph learning and feature selection into a uniform framework called DGL-UFS, which can capture higher level and more abstract representation than original low-level representation.
- 9
- Mask-Informed Deep Contrastive Incomplete Multi-View Clustering9
A mask-informed fusion network is introduced that aggregates incomplete multi-view information while considering the observation status of samples across various views as a mask, thereby reducing the adverse effects of missing values.
- 9
- Enhanced FCN for farmland extraction from remote sensing image9
This work reviewed relevant literature and utilized K-Means model, U-Net model and DeelLabV3 model respectively, to refine and make adjustments to farmland extraction model of RS image afterwards, to remedy flaws in current approaches and improve overall accuracy.
- 8
- 8
- Evaluation of Batvox 3.1 under conditions reflecting those of a real forensic voice comparison case (forensic_eval_01)8
The results show that the performance of the Batvox 3.1 system continued to improve as the amount of training data increased.
- OCT despeckling via weighted nuclear norm constrained non-local low-rank representation8
This work proposes an OCT despeckling method by using non-local, low-rank representation with weighted nuclear norm constraint, which shows superior performance compared with other state-of-the-art speckle removal techniques.
- 7
- 7
- 7
- 7
- Simultaneous Clustering and Optimization for Evolving Datasets7
This paper proposes a new variant of the alternating direction method of multipliers (ADMM) to solve the problem of evolving datasets efficiently and extensive empirical studies confirm the effectiveness of this method.
- Shape-optimizing mesh warping method for stereoscopic panorama stitching7
A novel shape-optimizing mesh warping method for stereoscopic panorama stitching, which aims to resolve shape distortion and unnatural rotation of traditional stitching methods, simultaneously coping with the challenges, misalignment, and stereoscopic inconsistency is proposed.
- Spectral Discrepancy and Cross-Modal Semantic Consistency Learning for Object Detection in Hyperspectral Images6
A novel network termed Spectral Discrepancy and Cross-Modal semantic consistency learning (SDCM) is proposed, which facilitates the extraction of consistent information across a wide range of hyperspectral bands while utilizing the spectral dimension to pinpoint regions of interest.
- 6
- Find True Collaborators: Banzhaf Index-based Cross View Alignment for Partially View-aligned Clustering6
A Banzhaf Index-driven cross-view aligNment method, dubbed BIN, which systematically evaluates each view sample's contribution to joint decision-making within a game-theoretic framework and ensures robust matching in complex misalignment scenarios.
- 6
- Cube is a good form: Hyperspectral band selection via multi-dimensional and high-order structure preserved clustering6
The proposed multi-dimensional high-order structure preserved clustering method for hyperspectral band selection, referred to as MHSPC, can effectively capture the spatial structure as well as the spectral correlation of original hyperspectral cube in both local and global perspectives.
- KRA: K-Nearest Neighbor Retrieval Augmented Model for Text Classification6
This work proposes a k-nearest neighbors retrieval augmented method (KRA) for deep-learning-based text classification models that significantly improves the classification performance of these models, including CNN, LSTM, BERT, and RoBERTa.
- 6
- 6
- A novel generative framework for designing pathogen-targeted antimicrobial peptides with programmable physicochemical properties5
A conditional Variational Autoencoder is first pretrained for generating AMPs with editable physicochemical properties, and a conditional diffusion model is developed to learn hidden representations of AMPs for targeting pathogens of interest, and construct corresponding MIC predictors for specific bacterial strains.
- 5
- SparseMVC: Probing Cross-view Sparsity Variations for Multi-view Clustering5
Adaptive Sparse Autoencoders for M ulti-V iew C lustering (SparseMVC), a framework with three key modules that extends sparsity handling from the data-level to view-level and mitigating the adverse effects of encoding discrepancies through sample-level dynamic weighting.
- 5
- Structure regularized consensus dynamic anchor graph learning for incomplete multi-view clustering5
Experiments show that the proposed SRCDAGL-IMC algorithm outperforms the state-of-the-art matrix factorization-based incomplete multi-view algorithms in terms of accuracy, normalized mutual information, purity and an effective alternating optimization method.
- 5
- Global Context Relation-Guided Feature Aggregation Network for Salient Object Detection in Optical Remote Sensing Images5
This work presents an end-to-end deep neural network for salient object detection in optical remote sensing images via global context relation-guided feature aggregation and designs a weighted binary cross entropy to capture local surrounding information of different pixels.
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- LRGR: Self-Supervised Incomplete Multi-View Clustering via Local Refinement and Global Realignment4
The Local Refinement and Global Realignment (LRGR) Self-supervised model is proposed for incomplete multi-view clustering, which includes two stages, designed to enhance the versatility of imputed representations through cross-view contrastive learning guided by view-specific prototypes.
- Spatially Resolved Transcriptomics Data Clustering with Tailored Spatial-scale Modulation4
This work introduces a novel spatially resolved transcriptomics data clustering network (TSstc), which surpasses existing state-of-the-art methods in clustering tasks and related downstream applications and uses a zero-inflated negative binomial model to capture the global probability distribution of gene expression profiles.
- 4
- 4
- 4
- Adaptive Discriminative Regions Learning Network for Remote Sensing Scene Classification4
An adaptive discriminative regions learning network for RSSC is proposed, referred as ADRL-Net, which locates discrim inative regions effectively for boosting the performance of RSSC by utilizing a novel self-supervision mechanism.
- 3
- Game Theory Inspired Cross-View Interaction Alignment for Partially View-Aligned Clustering3
This work proposes a Banzhaf game theory-driven cross-view Interaction method, dubbed BIN, which fundamentally mitigates the reliance on pre-aligned samples and enables robust clustering even under severe view misalignment, and conducts extensive and in-depth experiments on multi-view data.
- 3
- 3
- Dynamic Prediction of Drug–Target Interactions via Cross-Modal Feature Mapping with Learnable Association Information3
This work proposes a model named LAM-DTI, which introduces a learnable association information matrix as a flexible intermediary, which dynamically adjusts to capture accurate DTI association information, thereby enhancing cross-modal mapping within a unified latent space.
- 3
- TPDepth: Leveraging Text Prompts with ControlNet to Boost Diffusion-based Depth Estimation3
TPDepth, a diffusion-based, affine-invariant monocular depth estimator that incorporates textual semantics via a Text-Prompted ControlNet, achieves state-of-the-art results on NYUv2, KITTI, and ScanNet, and demonstrates competitive performance on two additional zero-shot benchmarks.
- Discriminative Binary Multi-View Clustering3
This work proposes a novel discriminative binary multi-view clustering (DBMVC) method that markedly outperforms other state-of-the-art methods in terms of effectiveness and efficiency.
- 3
- 3
- Robust Multi-View Clustering With a Unified Weight Learning Paradigm3
A novel robust multi-view clustering method with a unified weight learning paradigm that adaptively learns the quality of data points and the clustering capability of each view and improves the learning process of data quality.
- 3
- Balanced Multi-View Clustering2
A novel balanced multi-view clustering (BMvC) method is proposed, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view and achieves a better trade-off between the exploitation of view-specific patterns and the exploration of view-invariance patterns.
- Cross-level interaction and multi-granularity contrastive learning for multi-view clustering2
This work proposes a novel framework dubbed CLMGC: cross-level interaction and multi-granularity contrastive learning for multi-view clustering, which enhances information transfer between different levels and significantly improves the discriminative capability of the fine-grained semantic cluster, thus optimizing the overall performance of CLMGC.
- 2
- 2
- Advances in intelligent computing approaches for solving problems related to photonic crystal fibers2
Specific areas where PCF and IML are combined, including the prediction and optimization of optical properties, the design of polarization devices, fiber lasers and amplifiers, as well as the control and prediction of Supercontinuum generation are reviewed.
- Global Context and Enhanced Feature Guided Residual Refinement Network for 3D Cardiovascular Image Segmentation2
A novel deep neural network to segment the blood pool and myocardium from three dimensional cardiovascular images is introduced by fully exploiting the global context and complementary information encoded in different feature extraction layers, referred to as GCEFG-R2Net briefly.
- Single-Cell RNA-Sequencing Data Clustering via Locality Preserving Kernel Matrix Alignment2
This work presents a novel multiple kernel clustering framework for scRNA-seq data clustering via locality preserving kernel alignment, which can obtain superior results when compared with other state-of-the-art approaches.
- RGBD Salient Object Detection by Structured Low-Rank Matrix Recovery and Laplacian Constraint2
Both quantitative and qualitative experimental results on NLPR1000 and NJU400 show the advantage of the proposed RGBD salient object detection model.
- 1
- Efficient Layer-Wise Cross-View Calibration and Aggregation for Multispectral Object Detection1
A novel one-stage oriented detector for RGB-infrared object detection called the Layer-wise Cross-Modality calibration and Aggregation (LCMA) detector, which outperforms state-of-the-art methods in terms of both accuracy and computational efficiency.
- Generative Diffusion Contrastive Network for Multi-View Clustering1
This paper proposes anovel Stochastic Generative Diffusion Fusion (SGDF) method, which leverages a multiple generative mechanism for the multi-view feature of each sample and exhibits robustness against low-quality data.
- 1
- 1
- 1
- 1
- MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering1
An innovative Mixture of Ego-Graphs Fusion (MoEGF) is proposed, which constructs ego graphs and utilizes a Mixture-of-Experts network to implement fine-grained fusion of ego graphs at the sample level, rather than the conventional view-level fusion.
- 1
- 1
- 1
- 1
- –
- –
- CERA: Conflict-Explicit Reflective Agent for Multimodal Emotion Reasoning–
Conflict-Explicit Reflective Agent (CERA), a training-free, conflict-aware, and language-driven agentic framework for MER, significantly outperforms state-of-the-art training-free methods in both recognition accuracy and conflict interpretability, providing an effective training-free solution for complex emotional reasoning.
- –
- –
- –
- –
- PLA-MGRA: Multi-Granularity and Relation-Aware Learning for Efficient and Generalizable Protein-Ligand Binding Affinity Prediction–
PLA-MGRA is proposed, a minimalist and effective PLA prediction framework that captures both fine-grained atomic details and coarse grained functional semantics within the 3D structure of protein–ligand complexes, through multi-granularity learning.
- –
- –
- –
- –
- Hybrid Conditional Diffusion With Implicit Repair for Incomplete Multiview Clustering–
A two-stage framework, termed hybrid conditional diffusion with implicit repair for IMVC (HCDIR-IMVC), which simplifies the integration of diffusion models while improving the consistency and robustness of the recovered features and incorporates contrastive learning into the diffusion framework.
- –
- –
- –
- Low-light image enhancement with optical prior and frequency constraint–
This work introduces physical prior map grounded in K-M theory and selectively uses physical prior map based on its characteristics to enhance the network's capability in decomposing images into the illumination map and the reflectance map and enable the network to capture more comprehensive image information.
- –
- –
- DIG-FACE: De-biased Learning for Generalized Facial Expression Category Discovery–
This work proposes FER-GCD, an adversarial approach that integrates both implicit and explicit debiasing components that significantly improves accuracy on both old and new categories, achieving an average improvement of 9.8% over the baseline and outperforming state-of-the-art methods.
- –
- –
- –
- –
- –
- Research on Equipment Fault Prediction Method Based on Industrial Big Data–
This method improves the accuracy of industrial equipment fault prediction by preprocessing industrial data and establishing a prediction model based on a neural network, and the prediction time is reduced by extracting the main characteristic variables.
- –
- –
- –
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.