Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks236 from public data
- Contrastive Clustering862
An online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning and jointly learns representations and cluster assignments in an end-to-end manner is proposed.
- 650
- 472
- A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts438
This work proposes a simple yet effective generative model that takes as input noisy text descriptions about an unseen class and generates synthesized visual features for this class and shows that this method consistently outperforms the state of the art on the largest available benchmarks on Text-based Zero-shot Learning.
- COMIC: Multi-view Clustering Without Parameter Selection369
A novel objective function to project raw data into one space in which the projection embraces the geometric consistency (GC) and the cluster assignment consistency (CAC) and could achieve promising performance in learning view-specific representation and eliminating the heterogeneous gaps across different views.
- 366
- 363
- 350
- You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network296
A novel method, called you only look yourself (YOLY), which could be one of the first unsupervised and untrained neural networks for image dehazing which bypasses the conventional training paradigm of deep models on hazy-clean pairs or a large scale dataset, thus avoids the labor-intensive data collection and the domain shift issue.
- 279
- Partition level multiview subspace clustering277
A unified multiview subspace clustering model is proposed which incorporates the graph learning from each view, the generation of basic partitions, and the fusion of consensus partition which is seamlessly integrated and can be iteratively boosted by each other towards an overall optimal solution.
- Constructing the L2-Graph for Robust Subspace Learning and Subspace Clustering267
A novel method to eliminate the effects of the errors from the projection space (representation) rather than from the input space is presented and a method to construct a sparse similarity graph, called L2-graph is introduced.
- Deep subspace clustering with sparsity prior267
This paper proposes a novel subspace clustering method -- deeP subspAce clusteRing with sparsiTY prior with PARTY -- based on a new deep learning architecture that explicitly learns to progressively transform input data into nonlinear latent space and to be adaptive to the local and global subspace structure simultaneously.
- 251
- 206
- 199
- Deep Multiview Clustering by Contrasting Cluster Assignments191
This paper proposes a cross-view contrastive learning (CVCL) method that learns view-invariant representations and produces clustering results by contrasting the cluster assignments among multiple views and provides a theoretical analysis of soft cluster assignment alignment.
- 189
- Connections Between Nuclear-Norm and Frobenius-Norm-Based Representations183
It is proved that when the dictionary can provide enough representative capacity, FNR is exactly NNR even though the data set contains the Gaussian noise, Laplacian noise, or sample-specified corruption and otherwise, F NR and NNR are two solutions on the column space of the dictionary.
- 175
- Twin Contrastive Learning for Online Clustering173
It is found that when the data is projected into a feature space with a dimensionality of the target cluster number, the rows and columns of its feature matrix correspond to the instance and cluster representation, respectively.
- 172
- Structured graph learning for clustering and semi-supervised classification162
This paper proposes a graph learning framework to preserve both the local and global structure of data that uses the self-expressiveness of samples to capture the global structure and adaptive neighbor approach to respect the local structure.
- 157
- 157
- Noisy-Correspondence Learning for Text-to-Image Person Re-Identification156
A novel Robust Dual Embedding method (RDE) that can learn robust visual-semantic associations even with noisy correspondence and achieves state-of-the-art results both with and without synthetic noisy correspondences on all three datasets.
- 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.
- 156
- A Unified Framework for Representation-Based Subspace Clustering of Out-of-Sample and Large-Scale Data153
A unified framework that makes the representation-based subspace clustering algorithms feasible to cluster both the out-of-sample and the large-scale data, and gives an estimation for the error bounds by treating each subspace as a point in a hyperspace.
- Partially View-aligned Clustering151
A novel multi-view clustering method termed partially view-aligned clustering (PVC), which proposes to use a differentiable surrogate of the non-differentiable Hungarian algorithm and recasts it as a pluggable module to establish the category-level correspondence of the unaligned data.
- 150
- 148
- Decoupled Contrastive Multi-View Clustering with High-Order Random Walks147
A novel robust method, dubbed decoupled contrastive multi-view clustering with high-order random walks (DIVIDE), which leverages random walks to progressively identify data pairs in a global instead of local manner and embraces a novel MvC architecture to perform inter- and intra-view contrastive learning in different embedding spaces.
- DehazeGAN: When Image Dehazing Meets Differential Programming146
This work re-formulates the atmospheric scattering model into a novel generative adversarial network (DehazeGAN) that outperforms state-of-the-art methods in terms of PSNR, SSIM, and subjective visual quality.
- 138
- Deep Evidential Learning with Noisy Correspondence for Cross-modal Retrieval136
A generalized Deep Evidential Cross-modal Learning framework (DECL), which integrates a novel Cross- modal Evidential Learning paradigm (CEL) and a Robust Dynamic Hinge loss (RDH) with positive and negative learning to address the amplification problem and embrace higher robustness against high noise.
- Recent developments in application of single-cell RNA sequencing in the tumour immune microenvironment and cancer therapy135
Novel cell clusters of cancer-associated fibroblasts, T cells, tumour-associated macrophages and dendritic cells discovered after the application of scRNA-seq in TIME are concluded.
- 127
- Robust Subspace Clustering via Thresholding Ridge Regression127
A new method of robust subspace clustering is presented, called Thresholding Ridge Regression (TRR), which calculates the ell2-norm-based coefficients of a given data set and performs a hard thresholding operator; and then the coefficients are used to build a similarity graph for clustering.
- 120
- MaIR: A Locality-and Continuity-Preserving Mamba for Image Restoration114
A novel Mamba-based Image Restoration model (MaIR), which consists of Nested S-shaped Scanning strategy (NSS) and Sequence Shuffle Attention block (SSA), which preserves locality and continuity of the input images through the stripe-based scanning region and the S-shaped scanning path, respectively.
- 112
- 110
- Learning locality-constrained collaborative representation for robust face recognition100
A novel coding algorithm is proposed, called Locality-Constrained Collaborative Representation (LCCR), which introduces a kind of local consistency into coding scheme to improve the discrimination of the representation.
- 93
- 93
- Singe Image Rain Removal with Unpaired Information: A Differentiable Programming Perspective87
This work proposes RainRemoval-GAN (RRGAN), the first end-to-end adversarial model that generates realistic rain-free images using only unpaired supervision and demonstrates promising performance compared with nine state-of-the-art methods in terms of PSNR, SSIM, visual qualities and running time.
- 87
- OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization84
This work proposes a novel One-shot Pruning-Quantization (OPQ), the first work that reveals pre-trained model is sufficient for solving pruning and quantization simultaneously, without any complex iterative/manual optimization at the finetuning stage, and proposes a unified channel-wise quantization method that leads to low bit-rate allocation without introducing extra overhead.
- 71
- Semantic Invariant Multi-View Clustering With Fully Incomplete Information66
This work discovers the existence of invariant semantic distribution across different views, which enables SMILE to alleviate the cross-view discrepancy to learn consensus semantics without requiring any paired samples.
- 66
- Robust Object Re-identification with Coupled Noisy Labels65
A robust object ReID method dubbed Learning with Coupled Noisy Labels (LCNL), which first estimates the annotation confidences of samples and then adaptively divides the training pairs into four groups with the confidences to rectify the correspondences to achieve robust object ReID with theoretical guarantees.
- Deep anomaly detection in packet payload64
A novel feature engineering method is proposed to obtain the block-based features via block sequence extraction and block embedding and a neural network is designed to learn the representation of packet payload based on Long Short-Term Memory and Convolutional Neural Networks.
- Cascade Subspace Clustering63
This work proposes a deep learning based subspace clustering method which simultaneously learns a compact representation using a neural network and a clustering assignment by minimizing the discrepancy between pair-wise sample-centers distributions.
- SC2Net: Sparse LSTMs for Sparse Coding61
This work recasts ISTA as a recurrent neural network unit and shows its connection with the well-known long short term memory (LSTM) model, and presents a neural network to achieve sparse codes in an end-to-end manner.
- Multi-granularity Correspondence Learning from Long-term Noisy Videos54
Noise Robust Temporal Optimal traNsport (Norton) is proposed that addresses MNC in a unified optimal transport (OT) framework and employs video-paragraph and clip-caption contrastive losses to capture long-term dependencies based on OT.
- 54
- 54
- 54
- Graph Matching with Bi-level Noisy Correspondence52
This paper proposes a novel method termed Contrastive Matching with Momentum Distillation, with a robust quadratic contrastive loss which enjoys the following merits: i) better exploring the node-to-node and edge- to-edge correlations through a GM customized quadratics contrastive learning paradigm; ii) adaptively penalizing the noisy assignments based on the confidence estimated by the momentum teacher.
- 52
- 51
- Cross-modal Active Complementary Learning with Self-refining Correspondence50
A generalized Cross-modal Robust Complementary Learning framework (CRCL), which benefits from a novel Active Complementaries Loss (ACL) and an efficient Self-refining Correspondence Correction (SCC) to improve the robustness of existing methods.
- 49
- Image Clustering with External Guidance48
An externally guided clustering method (Text-Aided Clustering, TAC), which leverages the textual semantics of WordNet to facilitate image clustering, which achieves state-of-the-art performance on five widely used and three more challengingimage clustering benchmarks, including the full ImageNet-1K dataset.
- A survey on deep clustering: from the prior perspective41
This survey provides a comprehensive review of deep clustering methods by categorizing them into six types of prior knowledge and finds that in general the prior innovation follows two trends, namely, i) from mining to constructing, and ii) from internal to external.
- 41
- scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration38
It is observed that the omics difference varies in cells, and cells with smaller omics differences are easier to be integrated, thus benefiting the integration for the rest cells.
- 37
- 36
- 36
- A Qualitative Exploration of Self-Management Behaviors and Influencing Factors in Patients With Type 2 Diabetes35
The study findings identify clear challenges to self-management behavior and identify potential key influencing factors that could help patients translate healthcare provider’s information and instructions into action that improve compliance.
- 35
- An Approach for Information Systems Security Risk Assessment on Fuzzy Set and Entropy-Weight35
The approach of comprehensive eveluation is applied into integrating the respective risk assessment results of such three factors to obtain the final risk grade.
- Robust Variational Contrastive Learning for Partially View-unaligned Clustering34
A robust framework, dubbed VariatIonal ConTrAstive Learning (VITAL), designed to learn both common and specific information simultaneously simultaneously, which outperforms ten state-of-the-art deep clustering baselines, demonstrating its efficacy in both partially and fully aligned scenarios.
- Scalable Global Alignment Graph Kernel Using Random Features34
This paper proposes a new family of global alignment graph kernels, which take into account the global properties of graphs by using geometric node embeddings and an associated node transportation based on earth mover's distance and is positive-definite.
- fLRR: fast low‐rank representation using Frobenius‐norm31
Experimental results show that the method (i.e. fast LRR (fLRR)) performs well in terms of accuracy and computation speed in image clustering and motion segmentation compared with nuclear-norm-based LRR algorithm.
- Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification30
An Interactive Cross-modal Learning framework (ICL), which leverages human-centered interaction to enhance the discriminability of text queries through external multimodal knowledge, and introduces a novel Reorganization Data Augmentation (RDA) strategy based on information enrichment and diversity enhancement to enhance query discriminability.
- Robust Contrastive Multi-view Clustering against Dual Noisy Correspondence30
Contextually-spectral based correspondence refinery (CANDY) dexterously exploits inter-view similarities as context to uncover false negatives and employs a spectral-based module to denoise correspondence, alleviating the negative influence of false positives.
- Robust Contrastive Cross-modal Hashing with Noisy Labels29
This paper proposes a novel framework, termed Noise Resistance Cross-modal Hashing (NRCH), to learn hashing with noisy labels by overcoming two key challenges, i.e. noise overfitting and error accumulation.
- Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition29
Semantics-based Unpaired Multiview Learning (SUM-L) is proposed, the key idea is to build cross-view pseudopairs and do view-invariant alignment by leveraging the semantic information of videos.
- 29
- Semi-Supervised Multi-Modal Learning with Balanced Spectral Decomposition29
A Semi-supervised Multimodal Learning Network method (SMLN) which correlates different modalities by capturing the intrinsic structure and discriminative correlation of the multimedia data and will exactly balance all eigenvalues, thus being more competitive to existing methods.
- Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric28
This work develops a mutual information theory for deep fair clustering and accordingly designs a novel algorithm, dubbed FCMI, designed to achieve four characteristics highly expected by deepFair clustering, i.e., compact, balanced, and fair clusters, as well as informative features.
- Cross-modal discriminant adversarial network28
This work proposes CDM to project the generated results into a single common space, accompanying with a novel eigenvalue-based loss, which could push as much discriminative power as possible into all latent directions.
- 28
- Robust Duality Learning for Unsupervised Visible-Infrared Person Re-Identification27
A novel robust duality learning framework (RoDE) for UVI-ReID is proposed to mitigate the adverse impact of noisy pseudo-labels and a novel Robust Adaptive Learning mechanism (RAL) is proposed to dynamically prioritize clean samples while deprioritizing noisy ones, thus avoiding overemphasizing noise.
- 27
- 26
- 26
- 26
- 25
- Fast low rank representation based spatial pyramid matching for image classification25
This paper proposes using Low Rank Representation (LRR) to encode the descriptors under the framework of SPM to improve the generalizability and robustness and reformulate the rank-minimization problem as a truncated projection problem.
- Interactive Deep Clustering via Value Mining24
Interactive Deep Clustering (IDC), a plug-and-play method designed to boost the performance of pre-trained clustering models with minimal interaction overhead, and utilizes the user feedback to finetune the pre-trained clustering model.
- k-meansNet: When k-means Meets Differentiable Programming.24
A neural network which is a novel formulation of the vanilla $k$-means objective, with explicit interpretability in neural processing is proposed, which achieves promising performance comparing with 12 clustering methods on some challenging datasets.
- Online Fault Diagnosis for Photovoltaic Arrays Based on Fisher Discrimination Dictionary Learning for Sparse Representation23
FDDL for sparse representation is explored for diagnosing PV array faults, including line-to-line faults (LLF), open-circuit faults (OCF), and partial shading faults (PSF), with a small labeled dataset, and a dynamic normalization method without additional sensors is proposed to process transient data.
- 23
- 22
- 22
- 22
- 22
- 21
- 19
- 18
- A Dynamic Parameter Enhanced Network for distant supervised relation extraction18
A novel Dynamic Parameter Enhanced Network (DPEN) for Relation Extraction is developed, which introduces a parameter generator that can dynamically generates the network parameters according to the input query entity types and relation classes.
- Breakthroughs in diabetic retinopathy diagnosis and treatment using preclinical research models: current progress and future directions17
A narrative review explores recent advancements in basic science and translational research on DR diagnosis and treatment, leveraging cellular and animal models and elucidates the complex pathophysiological mechanisms underlying DR, particularly hyperglycaemia-triggered oxidative stress, inflammation and aberrant angiogenesis.
- LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification17
This work proposes LLaVA-ReID, a question model that generates targeted questions based on visual and textual contexts to elicit additional details about the target person in a dialogue-based retrieval task called interactive person re-identification (Inter-ReID).
- 16
- mixDA: mixup domain adaptation for glaucoma detection on fundus images16
This paper proposes a mixup domain adaptation ( mix DA) method that bridges domain adaptation with domain mixup to improve model performance across divergent glaucoma datasets and outperforms state-of-the-art methods by a large margin.
- 16
- MetaQ: fast, scalable and accurate metacell inference via single-cell quantization15
The authors propose MetaQ, a metacell algorithm that reduces cell number while preserving biological characteristics through a cell quantisation process, supporting both uni- and multi-omics data.
- 15
- ROAD: Robust Unsupervised Domain Adaptation with Noisy Labels14
A robust unsupervised domain adaptation framework (ROAD), which prevents the network model from overfitting noisy labels to capture accurate discrimination knowledge for domain adaptation, and a Robust Adaptive Weighted Learning mechanism (RSWL) is proposed to adaptively assign weights to each sample based on its reliability to enforce the model to focus more on reliable samples and less on unreliable samples, thereby mining robust discrimination knowledge against noisy labels in the source domain.
- 14
- 14
- Unsupervised Neural Rendering for Image Hazing13
Compared with existing haze generation methods, HazeGEN renders the hazy images in an unsupervised, learnable, and controllable manner, thus avoiding the labor-intensive efforts in paired data collection and the domain-shift issue in haze generation.
- Learning where to look: Semantic-Guided Multi-Attention Localization for Zero-Shot Learning.13
A semantic-guided multiattention localization model, which automatically discovers the most discriminative parts of objects for zero-shot learning without any human annotations is proposed, which improves the state-of-the-art results by a considerable margin.
- Locally linear representation for image clustering13
A novel scheme is proposed, where the similarity computation among different data points depends on both their pairwise distances and the linear representation relationships, and encodes each data point using a collection of data points that are close to the objective point.
- 13
- Trustworthy Visual-Textual Retrieval12
A novel Trust-Consistent Learning framework is proposed to endow visual-textual retrieval with uncertainty evaluation for trustworthy retrieval, and first models the matching evidence according to cross-modal similarity to estimate the uncertainty for cross-modal uncertainty-aware learning.
- Knowledge-Constrained Answer Generation for Open-Ended Video Question Answering12
A Knowledge-constrained Generative VideoQA Algorithm with an encoder-decoder pipeline, which enables out-of-domain answer generation through an adaptive external knowledge module and a multi-stream information control mechanism is proposed.
- Semi-supervised subspace learning with L2graph12
A semi-supervised subspace learning method which is inspired by the biological observation of similar inputs having similar codes (SISC), i.e., the same collection of cortical columns of the mammal's visual cortex is always activated by the similar stimuli is proposed.
- Learning with Noisy Correspondence10
The experimental results show the necessity of the explicit solution to the NC faced by not only the standard model training paradigm but also the pre-training and fine-tuning paradigms.
- Improve Interpretability of Neural Networks via Sparse Contrastive Coding10
A model-agnostic explanation method termed as Sparse Contrastive Coding (SCC) is proposed and verified its effectiveness in text classification and natural language inference and the superiority of the method over state-of-the-art methods in terms of interpretability and classification measurements is shown.
- 10
- Local Neighborhood Embedding for Unsupervised Nonlinear Dimension Reduction9
A novel algorithm, called Local NeighborhoodEmbedding (LNE), which preserves pairwise-distance basedsimilarity and reconstruction coefficient based similarity for finding the latent low dimensional structure of data and works well even in under-sampled case.
- Hierarchical Sparse Representation Clustering for High-Dimensional Data Streams8
A hierarchical sparse representation clustering framework for clustering high-dimensional data streams that enables the detection of outliers in high-dimensional data streams via the associated SRVs and introduces sparsity residual values (SRVs) to adaptively select representative data objects from the current landmark window.
- 8
- 8
- Two-step strategy—conjunctival flap covering surgery combined with secondary deep anterior lamellar keratoplasty for the treatment of high-risk fungal keratitis8
The two-step strategy is safe and effective in the treatment of high-risk FK by transforming intentional therapeutic penetrating keratoplasty during acute infection to later optical DALK, a practical strategy, especially in areas lacking fresh donor corneas and eye bank services.
- 8
- Relationship Quantification of Image Degradations7
By quantifying degradation relationship using DRI, it is revealed that a positive DRI consistently indicates performance improvement when a beneficial auxiliary degradation is incorporated during training and the proportion of auxiliary degradation is crucial to the anchor task performance.
- High-Speed Dynamic 3D Imaging with Sensor Fusion Splatting7
This work proposes a novel sensor fusion approach using Gaussian splatting, which combines RGB, depth, and event cameras to capture and reconstruct deforming scenes at high speeds, and significantly outperforms state-of-the-art techniques in both rendering fidelity and structural accuracy.
- 7
- 7
- 7
- Multimodal image-to-image translation between domains with high internal variability7
This work recast the training procedure as modeling distinct distributions which are observed sequentially, for example, when different classes are encountered over time, and proposes a novel generator regulating GAN (GR-GAN), which encourages the discriminator to teach the generator more effectively when it remembers more of the previously learned distributions.
- 7
- Inductive sparse subspace clustering7
An inductive spectral clustering algorithm called inductive SSC (iSSC) is proposed, which makes SSC feasible to cluster out-of-sample data and experimental results show that iSSC is promising in clustering out- of- sample data.
- 6
- Isolation and Culture of Human Meibomian Gland Ductal Cells6
The present study successfully isolated human MG ducts and cultured HMGDCs, providing a valuable in vitro model for investigating the mechanism of MGD and the potential therapeutic efficacy of rosiglitazone in treating hyperkeratinization of ducts in patients with MGD was identified.
- 6
- 6
- 6
- 5
- 5
- 5
- An Out-of-sample Extension of Sparse Subspace Clustering and Low Rank Representation for Clustering Large Scale Data Sets.5
A simple but effective method is proposed which makes SSC and LRR feasible to grouping new data and large scale data and adopts a "sampling, clustering, coding, and classifying" strategy.
- Fuzzy control method for lateral control of autonomous land vehicle5
A fuzzy logic controller for the road following of the autonomous land vehicle that does not need a precise vehicle model and has better adaptability to parameter variation of the vehicle than the PID.
- 4
- Cross-View Graph Consistency Learning for Invariant Graph Representations4
This paper empirically and experimentally demonstrates the effectiveness of the proposed cross-view graph consistency learning (CGCL) method, achieving competitive results on graph datasets in comparisons with several state-of-the-art algorithms.
- PrefAce: Face-Centric Pretraining with Self-Structure Aware Distillation4
A novel self-supervised face-centric pretraining framework, called PrefAce, which learns transferable video facial representation without labels, that can transfer across various facial analysis tasks, e.g., Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization.
- 4
- 4
- 4
- Learning Robust Multi-view Representation Using Dual-masked VAEs3
A holistic method, called Dual-masked Variational Autoencoders (DualVAE), which aims at learning robust multi-view representation and exhibits an innovative amalgamation of dual-masked prediction, mixture-of-experts learning, representation disentangling, and a joint loss function in wrapping up all components.
- An Empirical Study of Parameter Efficient Fine-tuning on Vision-Language Pre-train Model3
For downstream fine-tuning consistent with pre-training, data size no longer affects the performance, while the influence of fine-tunable parameter size is not monotonous, which could guide the choice of training strategy for various PEFTs.
- Consistency Enhancement-Based Deep Multiview Clustering via Contrastive Learning3
This paper shows how the above problems can be overcome and proposes a consistent enhancement-based deep MVC method via contrastive learning (CCEC), where semantic connection blocks are incorporated into a feature representation to preserve the consistent information among multiple views.
- 3
- Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embedding3
- Regularization techniques for high-dimensional data analysis3
This paper presents a meta-modelling architecture suitable for smart grids that was developed at the Tsinghua National Laboratory for Information Science and Technology (TNList) in China.
- 3
- Free-gram phrase identification for modeling Chinese text3
A novel approach for key phrase identification is proposed which is capable of identify phrases with all lengths and thus improves the coding efficiency and discrimination of the data representation.
- IBAS:Imperceptible Backdoor Attacks in Split Learning with Limited Information2
This paper designed a parrot model that learns the client’s feature space, enabling the server to obtain the intermediate activations of poisoned data, and designed an attack framework that modifies intermediate activations to influence the gradients.
- Disentangling Multi-view Representations via Curriculum Learning with Learnable Prior2
A novel curriculum learning approach that adjusts the whole model to learn view-consistent representations first and then progressively view-specific representations, and incorporates a mixture-of-experts layer and a disentangling module to further enhance the quality of the learned representations.
- PointCloud-Text Matching: Benchmark Datasets and a Baseline2
This paper presents and studies a new instance-level retrieval task: PointCloud-Text Matching (PTM), which aims to identify the exact cross-modal instance that matches a given point-cloud query or text query, and proposes a PTM baseline, named Robust PointCloud-Text Matching method (RoMa).
- 2
- Guest Editorial Special Issue on Discriminative Learning for Model Optimization and Statistical Inference2
Connecting discriminative learning with model optimization and inference is not only helpful in analyzing convergence and generalization of deep architectures but also offers new perspectives for understanding and developing generic deep learning models.
- 2
- 2
- Network Security Risk Assessment Based on Fuzzy Analytical Hierarchy Process2
An evaluation method based on fuzzy analytic hierarchy process (FAHP) for network security risk assessment is proposed and it provides a reliable basis for security risk control strategy of network security staff.
- 2
- 2
- 1
- FaverNet: All-in-One Video Restoration via Frequency-Discriminative Conditioning1
This work proposes FaverNet, a Frequency-guided All-in-one VidEo Restoration Network, which incorporates a Frequency-discriminative Conditioning Mechanism (FCM) and a Prompt-guided Alignment Mechanism (PAM), which enhances the degradation-awareness of the restoration process by conditioning the model with degradation cues extracted from frequency domain.
- 1
- 1
- Improving Representation Learning of Complex Critical Care Data with ICU-BERT1
ICU-BERT is introduced, a transformer-based model pre-trained on the MIMIC-IV database using a multi-task scheme to learn robust representations of complex ICU data with minimal preprocessing, offering an adaptable solution for clinical decision support across diverse applications.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- SSPHE special session on environmental science, pollution, and sustainability1
This special issue collects 12 papers on several facets of environmental pollution and energy management, among which are two articles with topics regarding decision-making for pollution control and energy efficiency evaluation.
- 1
- 1
- 1
- 1
- 1
- 1
- Design and Implement of Low Power Consumption SRAM Based on Single Port Sense Amplifier in 65 nm1
The single-port sense amplifier has solved problems in the traditional 8T cell structure, making the new structure of the memory at a greater depth still maintain good performance and lower power consumption.
- Locally linear representation for subspace learning and clustering1
The proposed algorithm can automatically encode each data point over a set of points that not only could denote the objective point with less residual error, but also are close to the point in Euclidean space.
- 1
- 1
- 1
- Stochastic Simulation of Self-similar Network Traffic Based on Mallat Algorithm1
Traffic modeling is introduced by decomposing traffic into wavelet coefficients and scale coefficients with different scale by mallat algorithm and adding up the random parts of the different coefficients into the simulation traffic.
- –
- Constrained Dipole Inversion Using Jointly Learned Local Field and Susceptibility Priors–
This work proposes a novel learning-based constrained reconstruction to integrate the jointly learned tissue field and susceptibility priors with the physics-based dipole inversion formalism such that the non-Gaussian model biased caused by the substantial errors in the estimated tissue field and the streaking artifacts in the tissue susceptibility can be effectively reduced.
- Bioengineering and omics approaches for Type 1 diabetes practical research: advancements and constraints–
Recent progress in genotypic and molecular profiles of Type 1 diabetes have become finer tuned and utilization and constraints in the realm of T1D are examined.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Study on External Power Receiving Planning of Receiving-end Grid in AC/DC Hybrid Background–
The reasonable scale of power receiving, the proportion of AC/ DC power transmitted and the infeed AC/DC terminal location for long-term development are analysed and comprehensive technical and economic comparisons among various feasible external power receiving schemes are conducted to form a recommended scheme.
- –
- Application of Mobile Geographic Information System Platform in High Voltage Grid Planning–
This work first analyzed the potentials of mobile GIS forgrid planning, then discussed the problems in high voltage grid planning, and finally proposed the system function and overall architecture design based onMobile GIS platform.
- Learning Graph Embedding with Limited Labeled Data: An Efficient Sampling Approach.–
A sampling-based training framework for semi-supervised graph embedding methods to achieve better performance with smaller training data set and verifies that the framework could extend the existing semi- supervised methods to the scenarios with the extremely small scale of labelled data.
- Identification of coherent generators based on clustering methods–
Two new algorithms based on clustering are proposed for the identification of coherent generators with optimal classification of generators based on given swing curves by introducing the validity index into the algorithm.
- Exploration and reflection on the cultivation of scientific research ability of postgraduates in neurology department–
Practice shows that improving measures put forward promoted the enthusiasm and subjective initiative of neuroscience academic postgraduates for scientific research, improved the quality of postgraduate education, and formed a certain basic and clinical research output.
- DNNRE: A Dynamic Neural Network for Distant Supervised Relation Extraction.–
A novel Dynamic Neural Network for Relation Extraction that can simultaneously handle the style shift problem and leverage mutual class relationships to enhance the prediction accuracy for long-tail classes is developed and can achieve superior performance over the state-of-the-art methods.
- –
- –
- –
- Principal Coefficients Embedding: Theory and Algorithm.–
This paper proves the equivalence between the Frobenius-norm and the Nuclear-norm-based representation and provides a new surrogate for the rank-minimization problem, and proposes a robust subspace learning algorithm, i.e., Principal Coefficients Embedding (PCE), which builds a similarity graph using k largest Frobenian norm-based coefficients and embeds the graph into a low-dimensional space.
- –
- Development of Intelligent Logistics Warehousing System Based on IOT Technology–
Based on RFID technology and wireless sense technology, analysis on the direction and model of intelligent logistics warehousing is made and explanation on the structure and function of the system is given.
- –
- –
- –
- The research of weak signal detection and simulation based on TWACS–
The result proves feasibility and validity of the dissertation approach and achieves good effect of TWACS weak signal combining notch technology and wavelet analysis.
- Self-Adaptive Management Policy for Scale-Free Networks–
A self-adaptive policy based on scale-free network that dynamically probes the rank of the entity based on the threshold of the metric and can reduce amount of collected data and eliminate the synchronization of data collecting is mentioned.
- Brief Introduction about HONET Comprehensive Work Switching Network FA16 System and Its Application in Huanghua Communication Network–
The principle,characteristic of FA16 switching network in detail, is introduced in detail and its concrete application in Huanghua communication network is proposed.
- Fault Diagnosis of Turbogenerator Units Vibration Based on Discrete BAM Neural Network–
Broad application prospect of BAM neural network method in the field of fault diagnosis can be envisaged because of some shortages of conventional diagnostic methods.
- –
- –
- Threshold decomposition of soft-morphological filters into function and set processing (FSP) morphological filters and order-statistic filters–
The necessary and sufficient condition for the SM's operators to be the morphological operators in the sense of complete lattice is given and the binary SM is proposed, which simplify the analysis of SM.
- Fuzzy morphology induced by threshold decomposition–
It is shown how one can use binary morphological operators, thresholding techniques and stacking properties to implement these FM's operators, and the VLSI implementation is simple and fast.
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.