Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks162 from public data
- 313
- Cervical cell classification with graph convolutional network129
A novel cervical cell classification method based on Graph Convolutional Network (GCN) that can achieve the better classification performance and also can be potentially used in automatic screening system of cervical cytology.
- DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system117
Two well-annotated benchmark datasets and organized challenges for the digestive-system pathological cell detection and tissue segmentation are released, in conjunction with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI).
- Super-resolution reconstruction of MR image with a novel residual learning network algorithm113
This work proposes a novel residual learning-based SR algorithm for MRI, which combines both multi-scale GRL and shallow network block-based local residual learning (LRL), which works effectively in capturing high-frequency details by learning local residuals.
- Adaptive color deconvolution for histological WSI normalization109
The proposed novel adaptive color deconvolution (ACD) algorithm can be efficiently solved and is effective to improve the performance of cancer image recognition, which is adequate for developing automatic CAD programs and systems based on WSIs.
- 95
- Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks89
This paper proposes a Sparse Sampling Transformer based on Uncertainty-Driven Ranking, dubbed UDR-S2Former, which can adaptively sample relevant image degradation information to model underlying degradation relationships and clearly outperforms state-of-the-art methods for all benchmarks.
- 77
- 64
- AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results63
This paper reviews the AIM 2019 challenge on constrained example-based single image super-resolution with focus on proposed solutions and results and gauges the state-of-the-art in single imagesuper-resolution.
- 60
- Graph Convolutional Networks for Cervical Cell Classification59
This paper presents a novel cervical cell classification method based on Graph Convolutional Network (GCN), which uses GCN to explore the image-level potential relationship for improving the classification performance.
- 56
- Remote sensing scene classification based on high-order graph convolutional network51
This paper presents a novel remote sensing scene classification method based on high-order graph convolutional network (H-GCN), which uses the attention mechanism to focus on the key components inside the image during CNN feature learning and high- order graph convolutionsal network is applied to investigate the class dependencies.
- Sparsity-guided saliency detection for remote sensing images50
A sparsity-guided saliency detection model for remote sensing images that uses a sparse representation to obtain the high- level global and background cues for saliency map integration and a Bayesian formula is applied to integrate the saliency maps generated by both types of high-level cues.
- 40
- 38
- 37
- Relevance-Aware Anomalous Users Detection in Social Network via Graph Neural Network36
An innovate Relevance-aware Anomalous Users Detection model (RAUD) is proposed, which extracts and learns both the explicit and implicit relevance from meta data based on heterogeneous information network (HIN) and GNNs.
- 32
- Encoding histopathology whole slide images with location-aware graphs for diagnostically relevant regions retrieval29
A novel framework for regions retrieval from WSI database based on location-aware graphs and deep hash techniques is proposed, which ensures the framework is efficient and adequate for practical large-scale W SI database.
- Encoding Histopathological WSIs Using GNN for Scalable Diagnostically Relevant Regions Retrieval27
A novel CBHIR framework for regions retrieval from WSI-database based on hierarchical graph neural networks (GNNs) is proposed, which makes the retrieval framework more sensitive to regions that are similar in tissue distribution.
- Positional encoding-guided transformer-based multiple instance learning for histopathology whole slide images classification26
A novel positional encoding-guided transformer-based multiple instance learning (PEGTB-MIL) method for histopathology WSI classification that utilizes positional encoding to effectively guide and reinforce MIL, leading to enhanced performance on downstream WSI classification tasks.
- Future Event Prediction Based on Temporal Knowledge Graph Embedding26
A new graph representation learning model, namely Recurrent Event Graph ATtention Network (RE-GAT), based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently is proposed.
- Deep Natural Language Processing for Search and Recommender Systems26
This tutorial first introduces deep learning based NLP technologies, including language understanding and language generation, and details how those technologies can be applied to common tasks in search and recommender systems, including query and document understanding, retrieval and ranking, and languagegeneration.
- 24
- 23
- Masked hypergraph learning for weakly supervised histopathology whole slide image classification22
A novel Masked HyperGraph Learning (MaskHGL) framework for weakly supervised histopathology WSI classification that exploits the non-pairwise correlations between patches with hypergraph and global message passing conducted by hypergraph convolution and shows a great improvement in quality and robustness.
- Generating region proposals for histopathological whole slide image retrieval22
A novel unsupervised region proposing method that can generate regions as predictions of lesions in histopathological WSI and a new semi-supervised hashing method for image retrieval that can achieve fast and precise image retrieval with small amount of labels are presented.
- Histopathology language-image representation learning for fine-grained digital pathology cross-modal retrieval21
This work proposes a novel histopathology language-image representation learning framework for fine-grained digital pathology cross-modal retrieval, which utilizes paired diagnosis reports to learn fine-grained semantics from the WSI.
- 20
- 19
- 19
- Prediction of Epidermal Growth Factor Receptor Mutation Subtypes in Non–Small Cell Lung Cancer From Hematoxylin and Eosin–Stained Slides Using Deep Learning17
An artificial intelligence-powered deep learning framework was developed for weakly supervised prediction of EGFR mutations in NSCLC from hematoxylin and eosin-stained histopathology whole-slide images and validated on unseen datasets.
- Evacuation Simulation of a Passenger Ship Fire Based on a Modified Cellular Automaton17
A modified cellular automaton is proposed to simulate passenger ship fire evacuation and shows that when the fire release rate increases from 3000 to 8000 kW s−2 for the same evacuation scenario, the earliest time that evacuees are in danger is 50% earlier.
- 17
- 17
- 15
- Pathology report generation from whole slide images with knowledge retrieval and multi-level regional feature selection13
An advanced method for pathology report generation from WSIs is presented, addressing the key challenges associated with the large size and complex pathological structures of these images and outperforms the state-of-the-art techniques.
- Sandformer: CNN and Transformer under Gated Fusion for Sand Dust Image Restoration13
An efficient hybrid structure for sand dust image restoration to solve the feature inconsistency issue between Transformer and CNN is proposed and demonstrated that SandFormer achieves significant performance improvements in synthetic and real dust scenes compared to previous sand image restoration methods.
- Saliency-constrained semantic learning for airport target recognition of aerial images13
This work proposes a fast automatic recognition framework for an airport target of a low-resolution remote sensing image under a complicated environment that utilizes a visual attention model for locating the salient region, and then detects possible candidate targets and extracts saliency-constrained scale invariant feature transform descriptors to build a high-level semantics model.
- Research on the content-based image retrieval technology13
The algorithm of the feature extraction and its corresponding characteristic matching algorithms of the content-based image retrieval technology were discussed and some directions worth further study for improving indexing mechanism and introducing the relevance feedback technology were pointed out.
- HASN: hybrid attention separable network for efficient image super-resolution12
This work uses depth-wise separable convolutions, fully connected layers, and activation functions as the basic feature extraction modules, and proposes the hybrid attention separable block, which combines channel attention and spatial attention, thus making use of their complementary advantages.
- 12
- 11
- Pan-Cancer Histopathology WSI Pre-Training With Position-Aware Masked Autoencoder11
A novel self-supervised learning framework for pan-cancer WSI-level representation pre-training with the designed position-aware masked autoencoder (PAMA) module with a kernel reorientation (KRO) strategy and an anchor dropout (AD) mechanism.
- 11
- 11
- 11
- Informative Retrieval Framework for Histopathology Whole Slides Images Based on Deep Hashing Network11
- 11
- Weakly supervised multi-modal contrastive learning framework for predicting the HER2 scores in breast cancer9
A novel weakly supervised multi-modal contrastive learning (WSMCL) framework to predict the HER2 scores in BC at the whole slide image (WSI) level and has the better HER2 scoring performance and outperforms the state-of-the-art methods.
- A deep‐learning model for predicting tyrosine kinase inhibitor response from histology in gastrointestinal stromal tumor8
An artificial intelligence‐based deep‐learning model that uses convolutional neural networks to analyze digitized hematoxylin and eosin staining in tumor histological sections to predict potential response to imatinib or avapritinib treatment in GIST patients shows comparable or better prediction of actual response to TKI than sequencing‐based screening.
- 8
- Slide-Based Graph Collaborative Training for Histopathology Whole Slide Image Analysis7
A generic WSI analysis pipeline SlideGCD is proposed that can be adapted to any existing Multiple Instance Learning (MIL) frameworks and improve their performance, and concurrently initializes and refines the slide representation, as a guide for message passing in the slide-based graph.
- Adaptive Graph Embedding Discriminant Projections7
This paper presents a novel DR method called adaptive graph embedding discriminant projections (AGEDP), which greatly enhances the intraclass compactness and interclass separability, but also adaptively performs neighbor parameter selection which considers the fact that local manifold structure of each sample is generally different.
- 7
- 7
- 7
- A metabolic fingerprint of ovarian cancer: a novel diagnostic strategy employing plasma EV-based metabolomics and machine learning algorithms6
It is demonstrated that the RF algorithm, combined with sensitive thermal separation probe-based mass spectrometry analysis of plasma EVs, can effectively identify OC patients with good accuracy, and the proposed approach could serve as a routine prescreening tool for ovarian cancer.
- Fuzzy K-means clustering with reconstructed information6
A Fuzzy K-Means Clustering with Reconstructed Information (FKMRI) method that combines the reconstruction term with a cluster weight variable to effectively capture the true nature of data structure, thereby enhancing the clustering capability of FKM in high-dimensional spaces.
- 6
- Semi-supervised Variational Temporal Convolutional Network for IoT Communication Multi-anomaly Detection6
SS-VTCN is designed to capture the normal patterns of the IoT traffic data based on the distribution whether it is labeled or not by learning their representations with key techniques such as Variational Autoencoders and Temporal Convolutional Network.
- Weakly supervised histopathological image representation learning based on contrastive dynamic clustering6
A weakly supervised framework that learns the feature representations of various lesion areas from histopathology whole slide images with a contrastive learning network as the backbone and a designed contrastive dynamic clustering module to embedding the lesion information into the featurerepresentations.
- Tracing Diagnosis Paths on Histopathology WSIs for Diagnostically Relevant Case Recommendation6
A novel approach for computer-aided cancer diagnosis named session-based histopathology image recommendation (SHIR), which summaries the information of a WSI while the pathologist browsing the WSI and actively recommends the relevant cases within similar image content from the database.
- 6
- Research of social recommendation based on social tag and trust relation6
The results generated from Epinions and Movielens experiments reveal that the proposed algorithm is superior to the existing Trust-based Social Recommendation or Social Tag Recommendation especially for active users with only a few rating records.
- Unsupervised texture segmentation based on latent topic assignment6
An effective solution for unsupervised texture segmentation by taking advantage of the latent Dirichlet allocation (LDA) model, which is able to extract the characteristic features of a texture primitive and group them into a topic based on their frequencies of co-occurrence.
- 6
- 5
- 5
- 5
- Deep Natural Language Processing for Search Systems5
This tutorial focuses on how deep natural language processing powers search systems in practice, and introduces basic concepts, elaborates associated challenges, reviews the state-of-the-art approaches, and covers end-to-end tasks in search systems with examples.
- PLSA-based pathological image retrieval for breast cancer with color deconvolution5
A novel pathological image retrieval method for breast cancer, which is based on stain component and probabilistic latent semantic analysis (pLSA) model, and the connection between the words of the codebook and the latent topics among images are modeled by pLSA.
- 4
- 4
- 4
- 4
- 4
- D-CrossLinkNet for Automatic Road Extraction from Aerial Imagery4
A novel encoder-decoder architecture D-CrossLinkNet is proposed for extracting roads from aerial images with better performance than other CNN-based methods (e.g. DeepLab, LinkNet and D-LinkNet).
- 4
- Pathology Image Retrieval by Block LBP Based pLSA Model with Low-Rank and Sparse Matrix Decomposition4
A novel pathology image retrieval method for breast cancer that firstly applies block Local Binary Pattern features to describe the spatial texture property of pathology image, and then uses low-rank and sparse matrix composition for describing the correlated and specific characteristics of visual words to construct the probabilistic latent semantic analysis model.
- 4
- 3
- 3
- Synthetic aperture radar ground target image generation based on improved Wasserstein generative adversarial networks with gradient penalty3
An improved Wasserstein GAN with gradient penalty (IWGAN-GP), which introduces dense connection in the generator, integrates feature information at different levels to achieve feature reuse, and alleviates the gradient disappearance problem caused by deep networks.
- 3
- A Group Control Method of Central Air-conditioning Chilled Water Pumps with the Aim of Energy Saving3
- 3
- Remote Sensing Image Change Detection Based on Low-Rank Representation3
An unsupervised approach based on low-rank representation (LRR) for change detection in remote sensing images is proposed and Experimental results show the effectiveness and feasibility of the proposed method.
- Satellite Recognition via Sparse Coding Based Probabilistic Latent Semantic Analysis3
A novel method called sparse coding (SC) based probabilistic latent semantic analysis (SC-pLSA) for satellite recognition, which performs sparse coding to explore the potential correlation between the descriptor and multiple words.
- 3
- 3
- 2
- 2
- 2
- 2
- Highlight area inpainting guided by illumination model2
A two-step algorithm based on the combination of the exemplar-based algorithm and the illumination model to deal with specular images, especially those contain saturated pixels in the highlight areas is proposed.
- Regularized least square discriminant projection and feature selection2
A novel joint discriminant analysis and feature selection method that employs regularized least square for graph construction and l2,1-norm minimization on projection matrix for feature selection and has lower computational cost than SR.
- 2
- 2
- Unsupervised Discriminant Analysis Based on the Local and Non-local Mean2
A novel method called unsupervised discriminant analysis based on the local and non-local mean for feature extraction is proposed, which is robust to outliers and overcomes the discriminant difficulty caused by outliers.
- Adapting pathology foundation models for continual cross-center WSI retrieval1
A continual learning framework that adapts pathology foundation models for continual cross-center WSI retrieval (CCBHIR) and aligns outputs of pre-trained pathology foundation models into a unified latent domain by generating instance-wise prompts that dynamically mitigate domain discrepancies.
- 1
- Multi-scale convolutional fusion network embedded with improved attention mechanism for polarimetric synthetic aperture radar image classification1
By embedding the MEZ-SE module into MCF-Net, MEZ-MCF-Net significantly improves the completeness of feature representation and enhances the ability to distinguish different land cover categories.
- Large Language Model Aided Birt-Hogg-Dube Syndrome Diagnosis with Multimodal Retrieval-Augmented Generation1
BHD-RAG is a multimodal retrieval-augmented generation framework that integrates DCLD-specific expertise and clinical precedents with MLLMs to improve BHD diagnostic accuracy, achieving superior accuracy and generating evidence-based descriptions closely aligned with expert insights.
- Progression-Free Survival Improvement of Localized Ocular Adnexal MALT Lymphoma Patients with Residual Lesions: Comparative Outcome of Postoperative Treatment Versus Watchful Waiting1
Overall, postoperative treatment is needed for primary localized OA-EMZL patients with residual lesions with residual lesions, and both radiotherapy and chemotherapy can be alternatives.
- 1
- 1
- 1
- 1
- 1
- Stain Standardization Capsule: A pre-processing module for histopathological image analysis1
A novel color standardization module named stain standardization capsule (SSC) is proposed based on the paradigm of capsules network and the corresponding dynamic routing algorithm that can learn and generate uniform stain separation outputs for histopathological images in various color appearance without the reference to manually selected template images.
- 1
- 1
- 1
- 1
- Local correlation discriminant analysis and its semi-supervised extension1
To further improve the discriminant power of LCDA, it is extended to semi-supervised case, which can make use of both labeled and unlabeled data to perform discriminant analysis.
- 1
- 1
- 1
- 1
- 1
- –
- Unified multi-prototype network with pretrained swin transformer for visual and audio open set recognition–
This work proposes a novel framework called multi-prototype network with Pretrained Swin Transformer (PST-MPN) for OSR, developed based on a novel multi-prototype learning mechanism combined with hybrid distance that significantly outperforms other baseline methods and obtains state-of-the-art performance for OSR on both visual and audio tasks.
- –
- –
- –
- –
- –
- –
- Report-Guided Cross-Modal Representation Learning for Predicting EGFR Mutations by Whole Slide Image–
- –
- Development of Daily Trading Strategies Based on A Quantitative Trading Decision Model–
This study established an LSTM model by using long-term and short-term memory networks and predicted the future prices of gold and bitcoin investment products and measured the risk of the developed decision model and evaluated the accuracy of the model.
- –
- Collaborative Representation Based Graph Embedding Discriminant Analysis for Face Recognition–
Experimental results on ORL, AR, FERET and Yale B face datasets show that compared to the CRP method, the proposed method improves the maximum recognition rate by 1%~4% and improves 2%~6% in noise and blur results, respectively.
- –
- –
- –
- –
- –
- –
- [Research of Electroencephalogram for Sleep Stage Based on Collaborative Representation and Kernel Entropy Component Analysis].–
The experimental results of sleep stage classification indicated that the CR-KECA method achieved the best performance compared with the original feature, CR feature, and CR-PCA feature with the classification accuracy of 68.74 +/- 0.46%, sensitivity and specificity.
- –
- –
- –
- Virtual Design Studio (VDS) - Development of an Integrated Computer Simulation Environment for Performance Based Design of Very-Low Energy and High IEQ Buildings–
A software platform for integrated, coordinated and optimized design of green building systems with low energy consumption, high indoor environmental quality (IEQ), and high level of sustainability, intended to assist collaborating architects, engineers and project management team members throughout from the early phases to the detailed building design stages.
- –
- –
- –
- –
- –
- Design and Implementation of A Business-Oriented Data Integration System–
A business-oriented data integration system is developed, which cannot only resolve the data integration between the heterogeneous source in Distributed Computing Environment, but also make the system's deployment and expansibility simple.
- –
- –
- Genetic Algorithm and Its Application in Shape-based Image Retrieval–
The experiment results show the Genetic Algorithm can efficiently select features, greatly improve the precision and recall, and shorten the retrieval time.
- Research on extensible markup language problem solving based on resolution principle–
An approach to XML problem solving by means of resolution principle is presented, where the subsumption and request of problem is formalized by XDD (XML declarative description), a language which employs XML as its bare syntax and enhances XML expressive power by employing declaratives description theory.
- The application of PLC in criticality alarm system–
By selecting a suitable programmable controller and the criticality alarm device, the alarm system has now been built up and used successfully in the Institute.
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.