Searcharxiv⌕ Search

arXiv subjects

Wenwen Min

Publications and source records attributed to Wenwen Min.

At least 19 recordsLinked to original sources
arXiv2026

FreqFLD: Towards All-in-One Facial Landmark Detection via Frequency Modulation

Recent progress in deep learning has significantly advanced facial landmark detection. However, most existing methods process features in a spatial-domain manner under a dataset-specific training paradigm, which overlooks the fact that facial landmark detection is inherently geometry-driven and sensitive to frequency variations, thereby limiting cross-dataset generalization under complex scenarios and hindering the development of a facial landmark detection model. To address this issue, we propose \textbf{FreqFLD}, a \textbf{freq}uency-modulated framework towards All-in-One \textbf{f}acial \textbf{l}andmark \textbf{d}etection. Specifically, FreqFLD introduces a Frequency Modulation Module (FreqMoM) to explicitly induce the frequency prior by decoupling and modulating low- and high-frequency components, which is then injected into subsequent feature modeling to enable balanced modeling of global facial structure and local landmark details. Furthermore, FreqFLD employs a Frequency-Modulated Mixture-of-Experts (FreqMoE), with expert selection adaptively conditioned on frequency-modulated priors, enabling flexible modeling of heterogeneous facial landmark patterns under diverse and challenging scenarios. To regularize frequency-consistent modeling under the All-in-One paradigm, we further introduce a Frequency-Consistent Routing (FreqCR) loss, which constrains the routing and assignment of frequency-aware experts to promote balanced expert utilization across diverse facial scenarios, thereby enabling stable expert specialization and achieving robust facial landmark detection. Extensive experiments demonstrate that the proposed FreqFLD achieves comparable performance on popular datasets. The code is available at: https://github.com/jkj1059657014/FreqFLD.

cs.CV↗
arXiv2026

Cross-Slice Knowledge Transfer via Masked Multi-Modal Heterogeneous Graph Contrastive Learning for Spatial Gene Expression Inference

While spatial transcriptomics (ST) has advanced our understanding of gene expression in tissue context, its high experimental cost limits its large-scale application. Predicting ST from pathology images is a promising, cost-effective alternative, but existing methods struggle to capture complex cross-slide spatial relationships. To address the challenge, we propose SpaHGC, a multi-modal heterogeneous graph-based model that captures both intra-slice and inter-slice spot-spot relationships from histology images. It integrates local spatial context within the target slide and cross-slide similarities computed from image embeddings extracted by a pathology foundation model. These embeddings enable inter-slice knowledge transfer, and SpaHGC further incorporates Masked Graph Contrastive Learning to enhance feature representation and transfer spatial gene expression knowledge from reference to target slides, enabling it to model complex spatial dependencies and significantly improve prediction accuracy. We conducted comprehensive benchmarking on seven matched histology-ST datasets from different platforms, tissues, and cancer subtypes. The results demonstrate that SpaHGC significantly outperforms the existing nine state-of-the-art methods across all evaluation metrics. Additionally, the predictions are significantly enriched in multiple cancer-related pathways, thereby highlighting its strong biological relevance and application potential.

cs.CV↗
arXiv2026

Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images

Spatial transcriptomics (ST) enables spot-level in situ expression profiling, but its high cost and limited throughput motivate predicting expression directly from HE-stained histology. Recent advances explore using score- or flow-based generative models to estimate the conditional distribution of gene expression from histology, offering a flexible alternative to deterministic regression approaches. However, most existing generative approaches omit explicit modeling of gene-gene dependencies, undermining biological coherence. Single-cell foundation models (sc-FMs), pre-trained across diverse cell populations, capture these critical gene relationships that histology alone cannot reveal. Yet, applying expression-only sc-FMs to histology-conditioned expression modeling is nontrivial due to the absence of a visual pathway, a mismatch between their pre-training and conditional ST objectives, and the scarcity of mixed-cell ST supervision. To address these challenges, we propose HINGE (HIstology-coNditioned GEneration), which retrofits a pre-trained sc-FM into a conditional expression generator while mostly preserving its learned gene relationships. We achieve this by introducing SoftAdaLN, a lightweight, identity-initialized modulation that injects layer-wise visual context into the backbone, coupled with an expression-space masked diffusion objective and a warm-start curriculum to ensure objective alignment and training stability. Evaluated on three ST datasets, ours outperforms state-of-the-art baselines on mean Pearson correlation and yields more accurate spatial marker expression patterns and higher pairwise co-expression consistency, establishing a practical route to adapt pre-trained sc-FMs for histology-conditioned spatial expression generation.

cs.CV↗
arXiv2026

SpaCRD: Multimodal Deep Fusion of Histology and Spatial Transcriptomics for Cancer Region Detection

Accurate detection of cancer tissue regions (CTR) enables deeper analysis of the tumor microenvironment and offers crucial insights into treatment response. Traditional CTR detection methods, which typically rely on the rich cellular morphology in histology images, are susceptible to a high rate of false positives due to morphological similarities across different tissue regions. The groundbreaking advances in spatial transcriptomics (ST) provide detailed cellular phenotypes and spatial localization information, offering new opportunities for more accurate cancer region detection. However, current methods are unable to effectively integrate histology images with ST data, especially in the context of cross-sample and cross-platform/batch settings for accomplishing the CTR detection. To address this challenge, we propose SpaCRD, a transfer learning-based method that deeply integrates histology images and ST data to enable reliable CTR detection across diverse samples, platforms, and batches. Once trained on source data, SpaCRD can be readily generalized to accurately detect cancerous regions across samples from different platforms and batches. The core of SpaCRD is a category-regularized variational reconstruction-guided bidirectional cross-attention fusion network, which enables the model to adaptively capture latent co-expression patterns between histological features and gene expression from multiple perspectives. Extensive benchmark analysis on 23 matched histology-ST datasets spanning various disease types, platforms, and batches demonstrates that SpaCRD consistently outperforms existing eight state-of-the-art methods in CTR detection.

cs.CV↗
arXiv2026

RTGMFF: Enhanced fMRI-based Brain Disorder Diagnosis via ROI-driven Text Generation and Multimodal Feature Fusion

Functional magnetic resonance imaging (fMRI) is a powerful tool for probing brain function, yet reliable clinical diagnosis is hampered by low signal-to-noise ratios, inter-subject variability, and the limited frequency awareness of prevailing CNN- and Transformer-based models. Moreover, most fMRI datasets lack textual annotations that could contextualize regional activation and connectivity patterns. We introduce RTGMFF, a framework that unifies automatic ROI-level text generation with multimodal feature fusion for brain-disorder diagnosis. RTGMFF consists of three components: (i) ROI-driven fMRI text generation deterministically condenses each subject's activation, connectivity, age, and sex into reproducible text tokens; (ii) Hybrid frequency-spatial encoder fuses a hierarchical wavelet-mamba branch with a cross-scale Transformer encoder to capture frequency-domain structure alongside long-range spatial dependencies; and (iii) Adaptive semantic alignment module embeds the ROI token sequence and visual features in a shared space, using a regularized cosine-similarity loss to narrow the modality gap. Extensive experiments on the ADHD-200 and ABIDE benchmarks show that RTGMFF surpasses current methods in diagnostic accuracy, achieving notable gains in sensitivity, specificity, and area under the ROC curve. Code is available at https://github.com/BeistMedAI/RTGMFF.

cs.CV↗
arXiv2026

FGTBT: Frequency-Guided Task-Balancing Transformer for Unified Facial Landmark Detection

Recently, deep learning based facial landmark detection (FLD) methods have achieved considerable success. However, in challenging scenarios such as large pose variations, illumination changes, and facial expression variations, they still struggle to accurately capture the geometric structure of the face, resulting in performance degradation. Moreover, the limited size and diversity of existing FLD datasets hinder robust model training, leading to reduced detection accuracy. To address these challenges, we propose a Frequency-Guided Task-Balancing Transformer (FGTBT), which enhances facial structure perception through frequency-domain modeling and multi-dataset unified training. Specifically, we propose a novel Fine-Grained Multi-Task Balancing loss (FMB-loss), which moves beyond coarse task-level balancing by assigning weights to individual landmarks based on their occurrence across datasets. This enables more effective unified training and mitigates the issue of inconsistent gradient magnitudes. Additionally, a Frequency-Guided Structure-Aware (FGSA) model is designed to utilize frequency-guided structure injection and regularization to help learn facial structure constraints. Extensive experimental results on popular benchmark datasets demonstrate that the integration of the proposed FMB-loss and FGSA model into our FGTBT framework achieves performance comparable to state-of-the-art methods. The code is available at https://github.com/Xi0ngxinyu/FGTBT.

cs.CV↗
arXiv2026

Supervision-by-Hallucination-and-Transfer: A Weakly-Supervised Approach for Robust and Precise Facial Landmark Detection

High-precision facial landmark detection (FLD) relies on high-resolution deep feature representations. However, low-resolution face images or the compression (via pooling or strided convolution) of originally high-resolution images hinder the learning of such features, thereby reducing FLD accuracy. Moreover, insufficient training data and imprecise annotations further degrade performance. To address these challenges, we propose a weakly-supervised framework called Supervision-by-Hallucination-and-Transfer (SHT) for more robust and precise FLD. SHT contains two novel mutually enhanced modules: Dual Hallucination Learning Network (DHLN) and Facial Pose Transfer Network (FPTN). By incorporating FLD and face hallucination tasks, DHLN is able to learn high-resolution representations with low-resolution inputs for recovering both facial structures and local details and generating more effective landmark heatmaps. Then, by transforming faces from one pose to another, FPTN can further improve landmark heatmaps and faces hallucinated by DHLN for detecting more accurate landmarks. To the best of our knowledge, this is the first study to explore weakly-supervised FLD by integrating face hallucination and facial pose transfer tasks. Experimental results of both face hallucination and FLD demonstrate that our method surpasses state-of-the-art techniques.

cs.CV↗
arXiv2025

GraphMMP: A Graph Neural Network Model with Mutual Information and Global Fusion for Multimodal Medical Prognosis

In the field of multimodal medical data analysis, leveraging diverse types of data and understanding their hidden relationships continues to be a research focus. The main challenges lie in effectively modeling the complex interactions between heterogeneous data modalities with distinct characteristics while capturing both local and global dependencies across modalities. To address these challenges, this paper presents a two-stage multimodal prognosis model, GraphMMP, which is based on graph neural networks. The proposed model constructs feature graphs using mutual information and features a global fusion module built on Mamba, which significantly boosts prognosis performance. Empirical results show that GraphMMP surpasses existing methods on datasets related to liver prognosis and the METABRIC study, demonstrating its effectiveness in multimodal medical prognosis tasks.

cs.CV↗
arXiv2025

BS-LDM: Effective Bone Suppression in High-Resolution Chest X-Ray Images with Conditional Latent Diffusion Models

Lung diseases represent a significant global health challenge, with Chest X-Ray (CXR) being a key diagnostic tool due to its accessibility and affordability. Nonetheless, the detection of pulmonary lesions is often hindered by overlapping bone structures in CXR images, leading to potential misdiagnoses. To address this issue, we develop an end-to-end framework called BS-LDM, designed to effectively suppress bone in high-resolution CXR images. This framework is based on conditional latent diffusion models and incorporates a multi-level hybrid loss-constrained vector-quantized generative adversarial network which is crafted for perceptual compression, ensuring the preservation of details. To further enhance the framework's performance, we utilize offset noise in the forward process, and a temporal adaptive thresholding strategy in the reverse process. These additions help minimize discrepancies in generating low-frequency information of soft tissue images. Additionally, we have compiled a high-quality bone suppression dataset named SZCH-X-Rays. This dataset includes 818 pairs of high-resolution CXR and soft tissue images collected from our partner hospital. Moreover, we processed 241 data pairs from the JSRT dataset into negative images, which are more commonly used in clinical practice. Our comprehensive experiments and downstream evaluations reveal that BS-LDM excels in bone suppression, underscoring its clinical value. Our code is available at https://github.com/diaoquesang/BS-LDM.

eess.IV↗
arXiv2025

ITCFN: Incomplete Triple-Modal Co-Attention Fusion Network for Mild Cognitive Impairment Conversion Prediction

Alzheimer's disease (AD) is a common neurodegenerative disease among the elderly. Early prediction and timely intervention of its prodromal stage, mild cognitive impairment (MCI), can decrease the risk of advancing to AD. Combining information from various modalities can significantly improve predictive accuracy. However, challenges such as missing data and heterogeneity across modalities complicate multimodal learning methods as adding more modalities can worsen these issues. Current multimodal fusion techniques often fail to adapt to the complexity of medical data, hindering the ability to identify relationships between modalities. To address these challenges, we propose an innovative multimodal approach for predicting MCI conversion, focusing specifically on the issues of missing positron emission tomography (PET) data and integrating diverse medical information. The proposed incomplete triple-modal MCI conversion prediction network is tailored for this purpose. Through the missing modal generation module, we synthesize the missing PET data from the magnetic resonance imaging and extract features using specifically designed encoders. We also develop a channel aggregation module and a triple-modal co-attention fusion module to reduce feature redundancy and achieve effective multimodal data fusion. Furthermore, we design a loss function to handle missing modality issues and align cross-modal features. These components collectively harness multimodal data to boost network performance. Experimental results on the ADNI1 and ADNI2 datasets show that our method significantly surpasses existing unimodal and other multimodal models. Our code is available at https://github.com/justinhxy/ITFC.

eess.IV↗
arXiv2024

Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer

At present, deep neural network methods have played a dominant role in face alignment field. However, they generally use predefined network structures to predict landmarks, which tends to learn general features and leads to mediocre performance, e.g., they perform well on neutral samples but struggle with faces exhibiting large poses or occlusions. Moreover, they cannot effectively deal with semantic gaps and ambiguities among features at different scales, which may hinder them from learning efficient features. To address the above issues, in this paper, we propose a Dynamic Semantic-Aggregation Transformer (DSAT) for more discriminative and representative feature (i.e., specialized feature) learning. Specifically, a Dynamic Semantic-Aware (DSA) model is first proposed to partition samples into subsets and activate the specific pathways for them by estimating the semantic correlations of feature channels, making it possible to learn specialized features from each subset. Then, a novel Dynamic Semantic Specialization (DSS) model is designed to mine the homogeneous information from features at different scales for eliminating the semantic gap and ambiguities and enhancing the representation ability. Finally, by integrating the DSA model and DSS model into our proposed DSAT in both dynamic architecture and dynamic parameter manners, more specialized features can be learned for achieving more precise face alignment. It is interesting to show that harder samples can be handled by activating more feature channels. Extensive experiments on popular face alignment datasets demonstrate that our proposed DSAT outperforms state-of-the-art models in the literature.Our code is available at https://github.com/GERMINO-LiuHe/DSAT.

cs.CV↗
arXiv2024

Pretrained-Guided Conditional Diffusion Models for Microbiome Data Analysis

Emerging evidence indicates that human cancers are intricately linked to human microbiomes, forming an inseparable connection. However, due to limited sample sizes and significant data loss during collection for various reasons, some machine learning methods have been proposed to address the issue of missing data. These methods have not fully utilized the known clinical information of patients to enhance the accuracy of data imputation. Therefore, we introduce mbVDiT, a novel pre-trained conditional diffusion model for microbiome data imputation and denoising, which uses the unmasked data and patient metadata as conditional guidance for imputating missing values. It is also uses VAE to integrate the the other public microbiome datasets to enhance model performance. The results on the microbiome datasets from three different cancer types demonstrate the performance of our methods in comparison with existing methods.

q-bio.GN↗
arXiv2024

Masked adversarial neural network for cell type deconvolution in spatial transcriptomics

Accurately determining cell type composition in disease-relevant tissues is crucial for identifying disease targets. Most existing spatial transcriptomics (ST) technologies cannot achieve single-cell resolution, making it challenging to accurately determine cell types. To address this issue, various deconvolution methods have been developed. Most of these methods use single-cell RNA sequencing (scRNA-seq) data from the same tissue as a reference to infer cell types in ST data spots. However, they often overlook the differences between scRNA-seq and ST data. To overcome this limitation, we propose a Masked Adversarial Neural Network (MACD). MACD employs adversarial learning to align real ST data with simulated ST data generated from scRNA-seq data. By mapping them into a unified latent space, it can minimize the differences between the two types of data. Additionally, MACD uses masking techniques to effectively learn the features of real ST data and mitigate noise. We evaluated MACD on 32 simulated datasets and 2 real datasets, demonstrating its accuracy in performing cell type deconvolution. All code and public datasets used in this paper are available at https://github.com/wenwenmin/MACD and https://zenodo.org/records/12804822.

cs.LG↗
arXiv2024

scASDC: Attention Enhanced Structural Deep Clustering for Single-cell RNA-seq Data

Single-cell RNA sequencing (scRNA-seq) data analysis is pivotal for understanding cellular heterogeneity. However, the high sparsity and complex noise patterns inherent in scRNA-seq data present significant challenges for traditional clustering methods. To address these issues, we propose a deep clustering method, Attention-Enhanced Structural Deep Embedding Graph Clustering (scASDC), which integrates multiple advanced modules to improve clustering accuracy and robustness.Our approach employs a multi-layer graph convolutional network (GCN) to capture high-order structural relationships between cells, termed as the graph autoencoder module. To mitigate the oversmoothing issue in GCNs, we introduce a ZINB-based autoencoder module that extracts content information from the data and learns latent representations of gene expression. These modules are further integrated through an attention fusion mechanism, ensuring effective combination of gene expression and structural information at each layer of the GCN. Additionally, a self-supervised learning module is incorporated to enhance the robustness of the learned embeddings. Extensive experiments demonstrate that scASDC outperforms existing state-of-the-art methods, providing a robust and effective solution for single-cell clustering tasks. Our method paves the way for more accurate and meaningful analysis of single-cell RNA sequencing data, contributing to better understanding of cellular heterogeneity and biological processes. All code and public datasets used in this paper are available at \url{https://github.com/wenwenmin/scASDC} and \url{https://zenodo.org/records/12814320}.

q-bio.GN↗
arXiv2024

Masked Graph Autoencoders with Contrastive Augmentation for Spatially Resolved Transcriptomics Data

With the rapid advancement of Spatial Resolved Transcriptomics (SRT) technology, it is now possible to comprehensively measure gene transcription while preserving the spatial context of tissues. Spatial domain identification and gene denoising are key objectives in SRT data analysis. We propose a Contrastively Augmented Masked Graph Autoencoder (STMGAC) to learn low-dimensional latent representations for domain identification. In the latent space, persistent signals for representations are obtained through self-distillation to guide self-supervised matching. At the same time, positive and negative anchor pairs are constructed using triplet learning to augment the discriminative ability. We evaluated the performance of STMGAC on five datasets, achieving results superior to those of existing baseline methods. All code and public datasets used in this paper are available at https://github.com/wenwenmin/STMGAC and https://zenodo.org/records/13253801.

q-bio.GN↗
arXiv2024

Multi-Slice Spatial Transcriptomics Data Integration Analysis with STG3Net

With the rapid development of the latest Spatially Resolved Transcriptomics (SRT) technology, which allows for the mapping of gene expression within tissue sections, the integrative analysis of multiple SRT data has become increasingly important. However, batch effects between multiple slices pose significant challenges in analyzing SRT data. To address these challenges, we have developed a plug-and-play batch correction method called Global Nearest Neighbor (G2N) anchor pairs selection. G2N effectively mitigates batch effects by selecting representative anchor pairs across slices. Building upon G2N, we propose STG3Net, which cleverly combines masked graph convolutional autoencoders as backbone modules. These autoencoders, integrated with generative adversarial learning, enable STG3Net to achieve robust multi-slice spatial domain identification and batch correction. We comprehensively evaluate the feasibility of STG3Net on three multiple SRT datasets from different platforms, considering accuracy, consistency, and the F1LISI metric (a measure of batch effect correction efficiency). Compared to existing methods, STG3Net achieves the best overall performance while preserving the biological variability and connectivity between slices. Source code and all public datasets used in this paper are available at https://github.com/wenwenmin/STG3Net and https://zenodo.org/records/12737170.

cs.CV↗
arXiv2024

High-Resolution Spatial Transcriptomics from Histology Images using HisToSGE

Spatial transcriptomics (ST) is a groundbreaking genomic technology that enables spatial localization analysis of gene expression within tissue sections. However, it is significantly limited by high costs and sparse spatial resolution. An alternative, more cost-effective strategy is to use deep learning methods to predict high-density gene expression profiles from histological images. However, existing methods struggle to capture rich image features effectively or rely on low-dimensional positional coordinates, making it difficult to accurately predict high-resolution gene expression profiles. To address these limitations, we developed HisToSGE, a method that employs a Pathology Image Large Model (PILM) to extract rich image features from histological images and utilizes a feature learning module to robustly generate high-resolution gene expression profiles. We evaluated HisToSGE on four ST datasets, comparing its performance with five state-of-the-art baseline methods. The results demonstrate that HisToSGE excels in generating high-resolution gene expression profiles and performing downstream tasks such as spatial domain identification. All code and public datasets used in this paper are available at https://github.com/wenwenmin/HisToSGE and https://zenodo.org/records/12792163.

eess.IV↗
arXiv2024

SpaDiT: Diffusion Transformer for Spatial Gene Expression Prediction using scRNA-seq

The rapid development of spatial transcriptomics (ST) technologies is revolutionizing our understanding of the spatial organization of biological tissues. Current ST methods, categorized into next-generation sequencing-based (seq-based) and fluorescence in situ hybridization-based (image-based) methods, offer innovative insights into the functional dynamics of biological tissues. However, these methods are limited by their cellular resolution and the quantity of genes they can detect. To address these limitations, we propose SpaDiT, a deep learning method that utilizes a diffusion generative model to integrate scRNA-seq and ST data for the prediction of undetected genes. By employing a Transformer-based diffusion model, SpaDiT not only accurately predicts unknown genes but also effectively generates the spatial structure of ST genes. We have demonstrated the effectiveness of SpaDiT through extensive experiments on both seq-based and image-based ST data. SpaDiT significantly contributes to ST gene prediction methods with its innovative approach. Compared to eight leading baseline methods, SpaDiT achieved state-of-the-art performance across multiple metrics, highlighting its substantial bioinformatics contribution.

cs.LG↗