Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks85 from public data
- Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning217
This paper proposes a novel TPT method, named DiffTPT, which leverages pre-trained diffusion models to generate diverse and informative new data, and incorporates augmented data by both conventional method and pre-trained stable diffusion to exploit their respective merits, improving the model’s ability to adapt to unknown new test data.
- Feed‐forward neural network optimized by hybridization of PSO and ABC for abnormal brain detection212
A novel automatic classification system based on particle swarm optimization and artificial bee colony and three new variants of feed‐forward neural network (FNN), consisting of IABAP‐fNN, ABC‐SPSO‐FNN, and HPA‐Fnn, which was superior to existing state‐of‐the‐art methods in terms of classification accuracy.
- Automated classification of brain images using wavelet-energy and biogeography-based optimization190
The results based on a 5 × 5-fold cross validation showed the performance of the proposed BBO-KSVM was superior to BP-NN, KSVM, and PSO- KSVM in terms of sensitivity and accuracy.
- Multimodal Transformer for Accelerated MR Imaging182
A multi-modal transformer (MTrans) is proposed, which is capable of transferring multi-scale features from the target modality to the auxiliary modality, for accelerated MR imaging and outperforms state-of-the-art methods on fastMRI and real-world clinical datasets.
- Task Transformer Network for Joint MRI Reconstruction and Super-Resolution169
An end-to-end task transformer network (T$^2$Net) is proposed for joint MRI reconstruction and super-resolution, which allows representations and feature transmission to be shared between multiple task to achieve higher-quality, super-resolved and motion-artifacts-free images from highly undersampled and degenerated MRI data.
- Multi-contrast MRI Super-Resolution via a Multi-stage Integration Network143
Extensive experiments demonstrate that the proposed MINet outperforms state-of-the-art multi-contrast MRI SR methods in terms of various metrics and the multi-stage integration module is able to excavate complex interactions among multi-Contrast features at different stages, leading to improved target-image quality.
- Specificity-Preserving Federated Learning for MR Image Reconstruction122
The core idea is to divide the MR reconstruction model into two parts: a globally shared encoder to obtain a generalized representation at the global level, and a client-specific decoder to preserve the domain-specific properties of each client, which is important for collaborative reconstruction when the clients have unique distribution.
- 110
- Visual Programming for Zero-Shot Open-Vocabulary 3D Visual Grounding97
This work proposes a novel visual programming approach for zero-shot open-vocabulary 3DVG, leveraging the capabilities of large language models (LLMs) and develops an innovative language-object correlation module to extend the scope of existing 3D object detectors into open-vocabulary scenarios.
- Sentence-level Prompts Benefit Composed Image Retrieval89
This work demonstrates that learning an appropriate sentence-level prompt for the relative caption (SPRC) is sufficient for achieving effective composed image retrieval and proposes to leverage pretrained V-L models, e.g., BLIP-2, to generate sentence- level prompts.
- Learning Federated Visual Prompt in Null Space for MRI Reconstruction77
FedPR is a new federated paradigm that adopts a powerful pre-trained model while only learning and communicating the prompts with few learnable parameters, thereby significantly reducing communication costs and achieving competitive performance on limited local data.
- Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution76
This study proposes a separable attention network (comprising high-intensity priority (HP) attention and low-intensity separation (LS) attention), named SANet, which is the first model to explore a separable attention mechanism that uses the auxiliary contrast to predict the high- and low-intensity regions.
- Brain MRI super-resolution using coupled-projection residual network65
Experiments show that the proposed CPRN achieves superior MRI super-resolution performance compared with the state-of-the-art, and a step-wise connection (CPRN_S) is designed, inspired by the human cognitive process.
- DONet: Dual-Octave Network for Fast MR Image Reconstruction53
The dual-octave network (DONet), which is capable of learning multiscale spatial-frequency features from both the real and imaginary components of MR data, for parallel fast MR image reconstruction, is proposed.
- 44
- 34
- A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers31
A comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate, and outlines a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base.
- Achieving flexible fairness metrics in federated medical imaging31
Evaluated across four clinical applications (polyp segmentation, fundus vascular segmentation, cervical cancer segmentation, and skin disease diagnosis), FlexFair outperforms state-of theart methods in both fairness and accuracy.
- Dual-Octave Convolution for Accelerated Parallel MR Image Reconstruction31
The Dual-Octave Convolution (Dual-OctConv), which is capable of learning multi-scale spatial-frequency features from both real and imaginary components, for fast parallel MR image reconstruction, shows a strong ability to capture richer representations of MR images, while at the same time greatly reducing the spatial redundancy.
- Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolution29
A real-world ×4 VSR dataset is built, namely MVSR4×, where low- and high-resolution videos are captured with different focal length lenses of a smartphone, respectively, and an effective alignment method is proposed, namely EAVSR, which takes the proposed multi-layer adaptive spatial transform network to refine the offsets provided by the pre-trained optical flow estimation network.
- From pretraining to privacy: federated ultrasound foundation model with self-supervised learning28
UltraFedFM surpasses the diagnostic accuracy of mid-level ultrasonographers and matches the performance of expert-level sonographers in the joint diagnosis of 8 common systemic diseases, marking a significant advancement in AI-driven ultrasound imaging for future clinical applications.
- 27
- Towards Instance-adaptive Inference for Federated Learning27
This paper presents a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework, and resorts to a parameter-efficient fine-tuning method, i.e., scale and shift deep features (SSF) upon a pre-trained model.
- Automated Classification of Brain MR Images Using Wavelet-Energy and Support Vector Machines25
The proposed wavelet-energy based new approach for automated classification of MR human brain images showed its performance was comparable with state-of-the-art algorithms and provided a new means to detect features indicative of abnormal brains.
- 24
- Surgical video workflow analysis via visual-language learning23
This work proposes a vision-language deep learning framework that incorporates intra- and inter- triplet modeling, termed I2TM, to explore the relationships among triplets and leverage the model understanding of the entire surgical process, thereby enhancing the accuracy and robustness of recognition.
- Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents20
V-RAG is proposed, a novel, vision-centric retrieval-augmented generation (RAG) framework that leverages a suite of multimodal vision encoders, each optimized for specific strengths, and a dedicated question-document relevance module that sets a new standard on document haystack benchmarks.
- Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning18
This paper solved FSCIL by leveraging the Vision-Language model and proposed a simple yet effective framework, named Learning Prompt with Distribution-based Feature Replay (LP-DiF), observing that simply using CLIP for zero-shot evaluation can substantially outperform the most influential methods.
- 16
- Rethinking Client Drift in Federated Learning: A Logit Perspective15
A new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models to enhance the quality of global logits, and adopts an adaptive mask to filter out the terrible soft labels of the global models, thereby preventing them to mislead local optimization.
- A Simple Review of Sparse Principal Components Analysis15
This review paper will mainly focus on the research about SPCA, where the basic models of PCA and SPC a, various algorithms and extensions of SPCa are summarized, and a comparison among the different kind of sparse penalties is made.
- 14
- 14
- 13
- The Research on Multi-Material 3D Vascularized Network Integrated Printing Technology13
A novel approach to fabricate 3D perfusable channels by using the combination of extrusion and inkjet techniques in an integrated manufacture process that can potentially provide a strategy for fabricating 3D vascularized channels and advance the development of culturing thick tissues in vitro.
- Digital Microdroplet Ejection Technology-Based Heterogeneous Objects Prototyping13
An integrate fabrication framework is presented to build heterogeneous objects (HEO) using digital microdroplets injecting technology and rapid prototyping and it is concluded that the method is effective for HEO.
- Federated Pseudo Modality Generation for Incomplete Multi-Modal MRI Reconstruction12
This paper proposes a novel communication-efficient federated learning framework (namely Fed-PMG) to address the missing modality challenge in federated multi-modal MRI reconstruction and demonstrates that the proposed method can outperform state-of-the-art methods and reach a performance similar to the ideal scenario.
- Neoadjuvant Savolitinib targeted therapy stage IIIA-N2 primary lung adenocarcinoma harboring MET Exon 14 skipping mutation: A case report12
It is presented that systemic treatment with the MET inhibitor savolitinib before surgery could provide the potential to prolong overall survival (OS) of patients with locally advanced potentially resectable NSCLC.
- PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models11
PiSA-Engine (Point-Self-Augmented-Engine), a new framework for generating instruction point-language datasets enriched with 3D spatial semantics, is introduced, observing that existing 3D MLLMs offer a comprehensive understanding of point clouds for annotation, while 2D MLLMs excel at cross-validation by providing complementary information.
- PCA via joint graph Laplacian and sparse constraint: Identification of differentially expressed genes and sample clustering on gene expression data11
The results demonstrate that gLSPCA is effective in identifying differentially expressed genes and sample clustering and provides several new clues for the exploration of causative factors of PAAD and HNSC.
- Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning9
T2I-PAL offers significant advantages: it eliminates the need for fully semantically annotated training images, thereby reducing the manual annotation workload, and it preserves the intrinsic mode of the CLIP model, allowing for seamless integration with any existing CLIP framework.
- Diffusion-Enhanced Test-Time Adaptation with Text and Image Augmentation8
A novel test-time adaptation method that utilizes a pre-trained generative model for multi-modal augmentation of each test sample from unknown new domains by combining augmented data from pre-trained vision and language models is introduced.
- A New Perspective to Boost Performance Fairness For Medical Federated Learning8
Fed-LWR is proposed to improve performance fairness from the perspective of feature shift, a key issue influencing the performance of medical FL systems caused by domain shift, and dynamically perceive the bias of the global model across all hospitals.
- VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering7
This work provides a Visual Question Answering (VQA) perspective to boost the performance of CIR and proposes a post-processing approach that outperforms state-of-the-art CIR methods on the CIRR and Fashion-IQ datasets.
- Bioinspired shape-changing nanofiber dressings for intelligent wrapping and promoting healing of superficial wounds7
In vivo results confirm that this multifunctional smart dressing promotes collagen synthesis and accelerates angiogenesis for accelerated wound healing, and is capable of rapid bending and autonomous wrapping around "artificial wounds" on a doll's body.
- 7
- 7
- Fluid–Structure Interaction Analysis of Perfusion Process of Vascularized Channels within Hydrogel Matrix Based on Three-Dimensional Printing7
Simulation results provide a method to optimize the perfusion parameters of tissue engineering, avoiding the perfusions failure caused by unreasonable perfusion pressure and hydrogel concentration and promoting the development of tissue Engineering culture in vitro.
- 6
- 6
- Towards Real-World Stickers Use: A New Dataset for Multi-Tag Sticker Recognition5
StickerTAG is introduced, the first multi-tag sticker dataset comprising a collected tag set with 461 tags and 13,571 sticker-tag pairs, designed to provide a deeper understanding of stickers.
- 5
- Reliable Federated Disentangling Network for Non-IID Domain Feature4
RfedDis is the FL approach to combine evidential uncertainty with feature disentangling, enhancing both performance and reliability in handling non-IID domain features, providing outstanding performance coupled with a high degree of reliability.
- CPT: Consistent Proxy Tuning for Black-box Optimization4
Different from Proxy-tuning, CPT additionally exploits the frozen large black-box model and another frozen small white-box model, ensuring consistency between training-stage optimization objective and test-time proxies, which benefits Proxy-tuning and enhances model performance.
- Prompt-driven efficient Open-set Semi-supervised Learning4
A prompt-driven efficient OSSL framework, called OpenPrompt, which can propagate class information from labeled to unlabeled data with only a small number of trainable parameters, and achieves a 4% improvement in terms of AUROC on outlier detection over a fully supervised model on CIFAR10.
- 4
- 3
- 3
- Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images3
A novel reliable multi-scale wavelet-enhanced transformer network, which can provide accurate segmentation results with reliability assessment and a novel uncertainty segmentation head based on the subjective logical evidential theory is introduced to generate the final segmentsation results.
- 3
- Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multitask Learning Perspective2
This work proposes an uncertainty-based impartial learning method that ensures balanced training across all tasks and considers both gradients and uncertainty information during backpropagation to further improve performance on the primary task.
- 2
- 2
- 2
- COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation2
This work presents a novel paradigm based on the vision-language model to learn SF-UniDA and hugely reduce the labeling costs on the basis of few-shot learning, which is formulated for the source model based on few-shot learning.
- 1
- Boost Protein Language Model with Injected Structure Information Through Parameter Efficient Fine-tuning1
Structures Information Injecting Tuning (SI-Tuning) effectively enhances the performance of PLMs by incorporating structural information in a parameter-efficient manner, making it a valuable strategy for applying large-scale PLM to broad biomedical downstream applications.
- Let Video Teaches You More: Video-to-Image Knowledge Distillation using Detection TRansformer for Medical Video Lesion Detection1
Through extensive experiments, the proposed V2I-DETR outperforms previous state-of-the-art methods by a large margin while achieving the real-time inference speed (30 FPS) as the image-based model.
- 1
- Time-aware sport goods sale prediction for healthcare with privacy-preservation1
The feasibility of the proposed SISP approach for healthcare, which is basically according to time series analysis, is validated and can quickly and accurately predict the future production or consumption scales of sport goods, in a privacy-aware way is validated.
- 1
- 1
- LJELSR: A Strengthened Version of JELSR for Feature Selection and Clustering1
A strengthened version of JELSR is proposed by adding the L1-norm constraint on the regularization term based on a previous model, and called LJELSR, to further improve the sparseness of the method and provide a new iterative algorithm to obtain the convergence solution.
- 1
- FedIGA: Improving Global Model Aggregation for Federated Self-Supervised Skeletal Action Recognition–
- Fairness in federated medical imaging: a systematic review through the dual fairness lens–
To the best of the knowledge, this constitutes the first systematic review to formally analyze the gradient-level conflict between collaboration fairness and group fairness in federated medical imaging, while also providing a structured causal analysis of equipment–demographic confounding, offering both a critical synthesis and actionable directions toward equitable AI-assisted healthcare.
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.