Multimodal Fusion

Ask about this topic

Overview

Multimodal fusion studies how to combine inputs such as images, text, audio, medical scans, sensor streams, and structured records so models can use their complementary information. Common approaches include early or late fusion, cross-attention and contrastive alignment, and adaptive gates or mixtures of experts that weight modalities by task, sample, or estimated reliability. Methods are tested across settings such as BraTS medical segmentation, CMU-MOSI and CMU-MOSEI sentiment analysis, RGB-thermal detection, and clinical prediction, with growing attention to missing, noisy, or misaligned inputs. A central open tension is that additional modalities can help when they add useful evidence, but can also introduce noise or let a dominant modality suppress weaker ones; robust gains and generalization beyond benchmark conditions remain difficult to establish.

Latest papers

CardsList

772 papers73 papers in the last four weeks, down 12% on the four weeks before. 0.4% of all new papers.

Apr 27, 2026

RACANet: Reliability-Aware Crowd Anchor Network for RGB-T Crowd Counting

RGB-Thermal (T) crowd counting aims to integrate visible-spectrum and thermal infrared information to improve the robustness of crowd density estimation in complex scenes. Although existing studies generally improve counting accuracy through cross-modal feature fusion, most current methods rely on implicit cross-modal fusion strategies and lack explicit modeling of local spatial discrepancies as well as fine-grained characterization of modality reliability at the positional level, thereby limiting the accuracy and interpretability of the fusion process. To address these issues, this paper proposes a two-stage fusion framework, RACANet, a Reliability-Aware Crowd Anchor Network for RGB-T crowd counting. First, we introduce a lightweight cross-modal alignment pretraining stage, which explicitly learns cross-modal semantic correspondences through crowd-prior supervision and local bidirectional soft matching. Then, based on the priors learned during pretraining, a Local Anchor Fusion Module (LAFM) is introduced in the formal training stage. This module generates local semantic anchors by aggregating features from highly reliable regions and further enables adaptive pixel-level feature redistribution with a local attention mechanism. In addition, we propose a discrepancy-aware consistency constraint to dynamically coordinate the reliability of regions where modal representations are consistent. Experiments conducted on two widely used benchmark datasets, RGBT-CC and Drone-RGBT, demonstrate that RACANet outperforms existing methods. The anonymous code is available at https://anonymous.4open.science/r/RACANet-9985.

Jinghao Shi, Mengqi Lei, Kunliang He +3

School of Computer Science, China University of Geosciences, Wuhan, Wuhan, China

Cross-Modal AlignmentCrowd CountingMultimodal FusionReliability-Aware Multimodal Fusion
AskPDF
Apr 27, 2026

Point Cloud Registration for Fusion between SPECT MPI and CTA Images

Clinical fusion of Single Photon Emission Computed Tomography Myocardial Perfusion Imaging (SPECT MPI) and Computed Tomography Angiography (CTA) remains limited by cross-modality misregistration and reliance on manual landmarks, which can hinder accurate ischemia localization and lesion-level functional assessment. To address this issue, we propose a registration and fusion framework for SPECT MPI and CTA that integrates functional and structural information for comprehensive cardiac evaluation. The proposed pipeline performs U-Net-based segmentation on both modalities. On SPECT MPI, only the left ventricle (LV) is extracted, and anatomical landmarks are automatically derived from characteristic LV structures. On CTA, both ventricles are segmented, and their spatial relationship is used to automatically define landmarks at the interventricular septal junction. Scale-space consistency preprocessing and landmark-driven coarse registration are applied to mitigate initial misalignment. Based on this initialization, multiple fine registration methods are evaluated on LV epicardial surface point clouds, including ICP, SICP, CPD, CluReg, FFD, and BCPD-plus-plus. The resulting transformations are then propagated to voxel-level resampling for high-precision SPECT-CTA fusion. In a retrospective cohort of 60 patients, the proposed framework preserved sub-millimeter coronary detail from CTA while accurately overlaying quantitative SPECT perfusion. Among the evaluated methods, BCPD-plus-plus achieved the highest accuracy with a mean point cloud distance of 1.7 mm. By combining robust initialization, comparative fine registration, and voxel-level fusion, the proposed approach provides a practical solution for myocardial ischemia localization and functional evaluation of coronary lesions, while remaining independent of any specific fine registration algorithm.

Ni Yao, Xiangyu Liu, Shaojie Tang +9

School of Computer Science and Artificial Intelligence, Zhengzhou University of Light Industry, Zhengzhou 450001, Henan, China · School of Automation, Xi’an University of Posts and Telecommunications, Xi’an, Shaanxi, 710121, China · Xi'an Key Laboratory of Advanced Control and Intelligent Process, Xi'an, Shaanxi, 710121, China +5

Medical ImagingMedical Image RegistrationPoint Cloud RegistrationMultimodal Fusion
AskPDF
Apr 27, 2026

CMGL: Confidence-guided Multi-omics Graph Learning for Cancer Subtype Classification

Motivation: Multi-omics integration can improve cancer subtyping, but modality informativeness and noise vary across cancer types and patients. Most graph methods for multi-omics data learn modality contributions within the downstream classification objective, leaving predictive reliability for each patient implicit. As a result, uninformative modalities can weaken the fused representation, while unreliable omics can introduce noisy patient relationships into graph propagation. To address these two problems, we propose CMGL, which produces a separate reliability estimate before fusion and uses consensus patient neighborhoods for graph classification. Results: CMGL estimates modality confidence for each patient through evidential deep learning, fixes these values during fusion across omics, and performs classification on an independently specified consistency graph. On four MLOmics cancer-subtype tasks and the 32-class pan-cancer task, CMGL consistently improves over the strongest baseline, surpassing it by 4.03% in average accuracy on the four single-cancer tasks. Its representations recover the PAM50 intrinsic subtypes of breast invasive carcinoma (BRCA), and the model trained on BRCA transfers without fine tuning to kidney renal clear cell carcinoma (KIRC), stratifying patients into prognostically distinct groups.

Boyang Fan, Hengchuang Yin, Siyu Yi +5

College of Computer Science, Sichuan University, Chengdu, China · Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Urumqi, China · College of Mathematics, Sichuan University, Chengdu, China +1

OncologyCancer Subtype ClassificationMultimodal Graph LearningMultimodal FusionMulti-Omics Data Integration
AskPDF
Apr 27, 2026

Open-Vocabulary Semantic Segmentation Network Integrating Object-Level Label and Scene-Level Semantic Features for Multimodal Remote Sensing Images

Semantic segmentation of multi-modal remote sensing imagery plays a pivotal role in land use/land cover (LULC) mapping, environmental monitoring, and precision earth observation. Current multi-modal approaches mainly focus on integrating complementary visual modalities, yet neglect the incorporating of non-visual textual data - a rich source of knowledge that can bridge semantic gaps between visual patterns and real-world concepts. To address this limitation, we propose TSMNet, a text supervised multi-modal open vocabulary semantic segmentation network that synergistically integrates textual supervision with visual representation for open-vocabulary semantic segmentation. Unlike conventional multi-modal segmentation frameworks, TSMNet introduces a dual-branch text encoder to extract both scene-level semantic and object-level label information from various textual data, enabling dynamic cross-modal fusion. These text-derived features dynamically interact with visual embeddings through the proposed text-guided visual semantic fusion module, enabling domain-aware feature refinement and human-interpretable decision-making. To verify our method, we innovatively construct two new multi-modal datasets, and carry out extensive experiments to make a comprehensive comparison between the proposed method and other state-of-the-art (SOTA) semantic segmentation models. Results demonstrate that TSMNet achieves superior segmentation accuracy while exhibiting robust generalization capabilities across diverse geographical and sensor-specific scenarios. This work establishes a new paradigm for explainable remote sensing analysis, demonstrating that textual knowledge integration significantly enhances model generalizability. The source code will be available at https://github.com/yeyuanxin110/TSMNet

Jinkun Dai, Yuanxin Ye, Peng Tang +4

Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, China · State-Province Joint Engineering Laboratory of Spatial Information Technology for High-Speed Railway Safety, Southwest Jiaotong University, Chengdu 611756, China · School of Artificial Intelligence, Wuhan University, Wuhan 430072, China +1

Remote Sensing Image SegmentationText-Guided Image SegmentationOpen-Vocabulary Semantic SegmentationMultimodal FusionSemantic SegmentationMultimodal Semantic Segmentation
AskPDF
Apr 27, 2026

Hierarchical Prototype-based Domain Priors for Multiple Instance Learning in Multimodal Histopathology Analysis

Digital pathology has fundamentally altered diagnostic workflows by enabling the computational analysis of gigapixel Whole Slide Images (WSIs), yet effectively deciphering their complex tumor microenvironments remains a formidable challenge. Existing Multiple Instance Learning (MIL) frameworks typically treat Whole Slide Images as unstructured bags of patches, discarding critical morphological semantics and spatial geometry. This lack of inductive bias often leads to overfitting on background noise and fails to align visual features with high-level diagnostic knowledge. To overcome these limitations, we propose the Hierarchical Prototype-based Domain Priors (HPDP) framework, a unified multimodal approach for joint histopathology diagnosis and prognosis. HPDP mitigates the data-driven "black box" issue by introducing a Morphologically Anchored Prototype System (MAPS), which anchors learning to interpretable morphological clusters, and a Sinusoidal Positional Encoder (SPE) to explicitly model tissue architecture. Furthermore, we bridge the semantic gap via a Hierarchical Cross-Modal Alignment (HCMA) module, using Large Language Model (LLM)-generated descriptions to contextually refine visual representations. Extensive experiments across seven cancer cohorts demonstrate that HPDP consistently achieves state-of-the-art performance with superior robustness and interpretability.

Xuemei Qiu, Dawei Fan, Yebin Huang +2

College of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou, 350002, China · Fujian Agriculture and Forestry University, Fuzhou, 350002, China · Department of Pathology, Clinical Oncology School of Fujian Medical University, and Fujian Cancer Hospital, Fuzhou, 350014, China +2

Cross-Modal AlignmentPrototype LearningHistopathology Image ClassificationMultimodal FusionMultiple Instance LearningWhole-Slide Image Analysis
AskPDF
Apr 27, 2026

LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization

Proactive watermarking offers a promising approach for deepfake tamper detection and localization in short-form videos. However, existing methods often decouple audio and visual evidence and assume that watermark signals remain reliable under real-world degradations, making tamper localization vulnerable to multimodal misalignment and compression distortions. Moreover, existing semi-fragile visual watermarking methods often degrade significantly under codec compression because their embedding bands overlap with compression-sensitive frequency regions. To address these limitations, we propose Layered Audio-Visual Anti-tampering Watermarking (LAVA), a calibration-aware audio-visual watermark fusion framework for deepfake tamper detection and localization. LAVA leverages cross-modal watermark fusion and calibration-aware alignment to preserve consistent and reliable tamper evidence under compression and audio-visual asynchrony, enabling robust tamper localization. Extensive experiments demonstrate that LAVA achieves near-perfect detection performance (AP = 0.999), remains robust to compression and multimodal misalignment, and significantly improves tamper localization reliability over existing audio-visual fusion baselines.

Bokang Zeng, Zheng Gao, Xiaoyu Li +2

School of Computer Science and Engineering UNSW Sydney Sydney, Australia · School of Information and Communication Technology Griffith University Brisbane, Australia

Audio WatermarkingDeepfake DetectionRobust WatermarkingMultimodal Fusion
AskPDF
Apr 26, 2026

Modeling Induced Pleasure through Cognitive Appraisal Prediction via Multimodal Fusion

Multimodal affective computing analyzes user-generated social media content to predict emotional states. However, a critical gap remains in understanding how visual content shapes cognitive interpretations and elicits specific affective experiences such as pleasure. This study introduces a novel computational model to infer video-induced pleasure via cognitive appraisal variables. The proposed model addresses four challenges: (1) noisy and inconsistent human labels, (2) the semantic gap between "positive emotions" and "pleasure," (3) the scarcity of pleasure-specific datasets, and (4) the limited interpretability of existing black-box fusion methods. Our approach integrates data-driven and cognitive theory-driven methods, using cognitive appraisal theory and a fuzzy model within an innovative framework. The model employs transformer-based architectures and attention mechanisms for fine-grained multimodal feature extraction and interpretable fusion to capture both inter- and intra-modal dynamics associated with pleasure. This enables the prediction of underlying appraisal variables, thereby bridging the semantic gap and enhancing model explainability beyond conventional statistical associations. Experimental results validate the efficacy of the proposed method in detecting video-induced pleasure, achieving a peak accuracy of 0.6624 in predicting pleasure levels. These findings highlight promising implications for affective content recommendation, intelligent media creation, and advancing our understanding of how digital media influences human emotions.

Nastaran Dab, Raziyeh Zall, Mohammadreza Kangavari

Department of Computer Engineering, Iran University of Science and Technology, Tehran, Iran.

Multimodal Model InterpretabilityMultimodal FusionAffective Computing
AskPDF
Apr 26, 2026

Emotion-Conditioned Short-Horizon Human Pose Forecasting with a Lightweight Predictive World Model

Short-term human pose prediction plays a crucial role in interactive systems, assistive robots, and emotion-aware human-computer interaction[1-3]. While current trajectory prediction models primarily rely on geometric motion cues, they often overlook the underlying emotional signals influencing human motion dynamics[4-5]. This paper investigates whether facial expression-derived emotion embeddings can provide auxiliary conditional signals for short-term pose prediction. To further evaluate multimodal conditionation in a recursive prediction setting, we propose a lightweight autoregressive predictive world model that performs 15-step rolling pose prediction. This framework combines pose keypoints with emotion embeddings through a learnable gating mechanism and performs autoregressive unfolding prediction using a recurrent sequence model based on a two-layer LSTM architecture. Experiments were conducted on two small-scale pose-emotion video datasets: controlled motion sequences with minimal facial expression changes and, natural emotion-driven motion sequences with considerable facial expression changes. The results show that simple multimodal fusion does not consistently improve prediction accuracy, while normalized gating fusion significantly enhances the performance of emotion-driven motion sequences. Furthermore, counterfactual perturbation experiments demonstrate that the predicted trajectory exhibits measurable sensitivity to changes in multimodal input, suggesting that facial expression embeddings act as auxiliary conditional signals rather than redundant features. In summary, these results indicate that incorporating facial expression-derived emotion embeddings into emotion-conditional short-term pose prediction based on a lightweight predictive world model architecture is a feasible approach.

Jingni Huang, Peter Bloodsworth

Gated Multimodal FusionHuman Motion GenerationMultimodal FusionMultimodal Learning
AskPDF
Apr 25, 2026

A Heterogeneous Two-Stream Framework for Video Action Recognition with Comparative Fusion Analysis

Most two-stream action recognition networks apply the same convolutional backbone to both RGB and optical flow streams, ignoring the fact that the two modalities have fundamentally different structural properties. Optical flow captures fine-grained motion patterns, while RGB frames carry rich appearance and scene context - treating them identically discards this distinction. We propose DualStreamHybrid, a heterogeneous two-stream architecture that assigns each stream a backbone suited to its input: a pretrained ViT-Tiny/16 for RGB frames, and a MobileNetV2 trained from scratch on a 20-channel stacked optical flow representation. A learned projection layer maps the two differently-sized feature vectors to a common dimensionality before fusion, enabling the two streams to interact without forcing architectural symmetry. We design five fusion strategies within a unified framework - late fusion, concatenation, cross-attention, weighted fusion, and gated fusion - and evaluate them on UCF11 (1,600 videos, 11 classes) and UCF50 (6,681 videos, 50 classes) to study how fusion behaviour scales with dataset size. On UCF11, cross-attention achieves 98.12% test accuracy, outperforming the RGB-only ViT-Tiny baseline of 95.94%, which suggests that explicit inter-modal attention is particularly effective on smaller, less complex datasets. On UCF50, weighted fusion reaches 96.86% and proves the most consistent strategy across both benchmarks. The learned stream weights reveal an interesting pattern: UCF11 sees near-equal modality contribution (RGB: 0.507, flow: 0.493), while UCF50 favours the RGB stream slightly more (RGB: 0.554, flow: 0.446) - arguably reflecting the larger and more visually diverse action space. Taken together, these results suggest that even a lightweight motion stream meaningfully complements a strong appearance encoder, and that the optimal fusion strategy depends on dataset scale.

Md. Afzalur Rahaman, Tahmid Rahman

Department of Computer Science & Engineering Hamdard University Bangladesh Munshiganj, Bangladesh

Video Action RecognitionCross-Modal AttentionMultimodal FusionFeature Fusion
AskPDF
Apr 25, 2026

Contrastive Learning for Multimodal Human Activity Recognition with Limited Labeled Data

Human activity recognition serves as the foundation for various emerging applications. In recent years, researchers have used collaborative sensing of multi-source sensors to capture complex and dynamic human activities. However, multimodal human activity sensing typically encounters highly heterogeneous data across modalities and label scarcity, resulting in an application gap between existing solutions and real-world needs. In this paper, we propose CLMM, a general contrastive learning framework for human activity recognition that achieves effective multimodal recognition with limited labeled data. CLMM employs a novel two-stage training strategy. In the first stage, CLMM employs a CNN-DiffTransformer encoder to capture cross-modal shared information by extracting local and global features. Meanwhile, a hard-positive samples weighting algorithm enhances gradient propagation to reinforce shared learning. In the second stage, a dual-branch architecture combining quality-guided attention and bidirectional gated units captures modality-specific information, while a primary-auxiliary collaborative training strategy fuses both shared and modality-specific information. Experimental results on three public datasets demonstrate that CLMM significantly improves state-of-the-art baselines in both recognition accuracy and convergence performance.

Long Jing, Zhixiong Yang, Yajun Zhang +1

College of Computer Science, Northwest University, Xi’an, China · Xinjiang University, Urumqi, China

Cross-Modal Representation LearningHuman Activity RecognitionMultimodal Contrastive LearningMultimodal FusionData-Efficient Learning
AskPDF
Apr 25, 2026

DARC-CLIP: Dynamic Adaptive Refinement with Cross-Attention for Meme Understanding

Memes convey meaning through the interaction of visual and textual signals, often combining humor, irony, and offense in subtle ways. Detecting harmful or sensitive content in memes requires accurate modeling of these multimodal cues. Existing CLIP-based approaches rely on static fusion, which struggles to capture fine grained dependencies between modalities. We propose DARC-CLIP, a CLIP-based framework for adaptive multimodal fusion with a hierarchical refinement stack. DARC-CLIP introduces Adaptive Cross-Attention Refiners to for bidirectional information alignment and Dynamic Feature Adapters for task-sensitive signal adaptation. We evaluate DARC-CLIP on the PrideMM benchmark, which includes hate, target, stance, and humor classification, and further test generalization on the CrisisHateMM dataset. DARC-CLIP achieves highly competitive classification accuracy across tasks, with significant gains of +4.18 AUROC and +6.84 F1 in hate detection over the strongest baseline. Ablation studies confirm that ACAR and DFA are the main contributors to these gains. These results show that adaptive cross-signal refinement is an effective strategy for multimodal content analysis in socially sensitive classification.

Qiyuan Jin

The Hong Kong University of Science and Technology

VLM AdaptationHate Speech DetectionMultimodal ClassificationCross-Modal AttentionMultimodal FusionHarmful Meme Detection
AskPDF
Apr 24, 2026

Text-Guided Multimodal Unified Industrial Anomaly Detection

Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing unsupervised methods suffer from two critical limitations: ambiguous cross-modal alignment caused by the lack of high-level semantic guidance and insufficient geometric modeling for RGB-to-3D feature mapping. To address these issues, we propose a unified multimodal industrial anomaly detection framework guided by text semantics. The framework consists of two core modules: a Geometry-Aware Cross-Modal Mapper to preserve geometric structure during modality conversion, and an Object-Conditioned Textual Feature Adaptor to align multimodal features with semantic priors. Furthermore, we establish a unified learning paradigm for multimodal industrial anomaly detection, which breaks the one-model-one-class constraint and enables accurate anomaly detection across diverse classes using a single model. Extensive experiments on the MVTec 3D-AD and Eyecandies datasets demonstrate that our method achieves state-of-the-art performance in classification and localization under unsupervised settings.

Zewen Li, Shuo Ye, Zitong Yu +2

School of Computer Science & Software Engineering, Shenzhen University, China, 518060 · School of Computing and Information Technology, Great Bay University, Dongguan, 523000,China

Unified Multimodal ModelsIndustrial Anomaly DetectionUnsupervised Anomaly DetectionMultimodal Anomaly DetectionMultimodal FusionAnomaly Detection
AskPDF
Apr 23, 2026

MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment

Universal Multimodal Retrieval (UMR) aims to map different modalities (e.g., visual and textual) into a shared embedding space for multi-modal retrieval. Existing UMR methods can be broadly divided into two categories: early-fusion approaches, such as Marvel, which projects visual features into the language model (LM) space for integrating with text modality, and late-fusion approaches, such as UniVL-DR, which encode visual and textual inputs using separate encoders and obtain fused embeddings through addition. Our pilot study reveals that Marvel exhibits visual modality collapse, which is characterized by the model's tendency to disregard visual features while depending excessively on textual cues. In contrast, although UniVL-DR is less affected by this issue, it is more susceptible to semantic misalignment, where semantically related content is positioned far apart in the embedding space. To address these challenges, we propose MiMIC, which introduces two key innovations: (1) a fusion-in-decoder architecture for effective multimodal integration, and (2) robust training through single modality mixin and random caption dropout. Experiments on the WebQA+ and EVQA+ datasets, where image in documents or queries might lack captions, indicate that MiMIC consistently outperforms both early- and late-fusion baselines.

Juan Li, Chuanghao Ding, Xujie Zhang +1

State Key Laboratory for Novel Software Technology, Nanjing University

Cross-Modal LearningCross-Modal AlignmentCross-Modal RetrievalMultimodal FusionMultimodal Understanding
AskPDF
Apr 22, 2026

Semi-Supervised Flow Matching for Mosaiced and Panchromatic Fusion Imaging

Fusing a low resolution (LR) mosaiced hyperspectral image (HSI) with a high resolution (HR) panchromatic (PAN) image offers a promising avenue for video-rate HR-HSI imaging via single-shot acquisition, yet its severely ill-posed nature remains a significant challenge. In this work, we propose a novel semi-supervised flow matching framework for mosaiced and PAN image fusion. Unlike previous diffusion-based approaches constrained by specific protocols or handcrafted assumptions, our method seamlessly integrates an unsupervised scheme with flow matching, resulting in a generalizable and efficient generative framework. Specifically, our method follows a two-stage training pipeline. First, we pretrain an unsupervised prior network to produce an initial pseudo HR-HSI. Building on this, we then train a conditional flow matching model to generate the target HR-HSI, introducing a random voting mechanism that iteratively refines the initial HR-HSI estimate, enabling robust and effective fusion. During inference, we employ a conflict-free gradient guidance strategy that ensures spectrally and spatially consistent HR-HSI reconstruction. Experiments on multiple benchmark datasets demonstrate that our method achieves superior quantitative and qualitative performance by a significant margin compared to representative baselines. Beyond mosaiced and PAN fusion, our approach provides a flexible generative framework that can be readily extended to other image fusion tasks and integrated with unsupervised or blind image restoration algorithms.

Peiming Luo, Nan Wang, Litong Liu +4

Southeast University · Hunan University

Flow MatchingMulti-Source Image FusionHyperspectral ImagingMultimodal Fusion
AskPDF
Apr 21, 2026

Structure-Semantic Decoupled Modulation of Global Geospatial Embeddings for High-Resolution Remote Sensing Mapping

Fine-grained high-resolution remote sensing mapping typically relies on localized visual features, which restricts cross-domain generalizability and often leads to fragmented predictions of large-scale land covers. While global geospatial foundation models offer powerful, generalizable representations, directly fusing their high-dimensional implicit embeddings with high-resolution visual features frequently triggers feature interference and spatial structure degradation due to a severe semantic-spatial gap. To overcome these limitations, we propose a Structure-Semantic Decoupled Modulation (SSDM) framework, which decouples global geospatial representations into two complementary cross-modal injection pathways. First, the structural prior modulation branch introduces the macroscopic receptive field priors from global representations into the self-attention modules of the high-resolution encoder. By guiding local feature extraction with holistic structural constraints, it effectively suppresses prediction fragmentation caused by high-frequency detail noise and excessive intra-class variance. Second, the global semantic injection branch explicitly aligns holistic context with the deep high-resolution feature space and directly supplements global semantics via cross-modal integration, thereby significantly enhancing the semantic consistency and category-level discrimination of complex land covers. Extensive experiments demonstrate that our method achieves state-of-the-art performance compared to existing cross-modal fusion approaches. By unleashing the potential of global embeddings, SSDM consistently improves high-resolution mapping accuracy across diverse scenarios, providing a universal and effective paradigm for integrating geospatial foundation models into high-resolution vision tasks.

Jienan Lyu, Miao Yang, Jinchen Cai +4

Sun Yat-Sen University · Tsinghua University

Remote Sensing Image SegmentationGeospatial Foundation ModelsCross-Modal AlignmentSpatial GeneralizationMultimodal Fusion
AskPDF
Apr 20, 2026

A Proxy Consistency Loss for Grounded Fusion of Earth Observation and Location Encoders

Supervised learning with Earth observation inputs is often limited by the sparsity of high-quality labeled or in-situ measured data to use as training labels. With the abundance of geographic data products, in many cases there are variables correlated with - but different from - the variable of interest that can be leveraged. We integrate such proxy variables within a geographic prior via a trainable location encoder and introduce a proxy consistency loss (PCL) formulation to imbue proxy data into the location encoder. The first key insight behind our approach is to use the location encoder as an agile and flexible way to learn from abundantly available proxy data which can be sampled independently of training label availability. Our second key insight is that we will need to regularize the location encoder appropriately to achieve performance and robustness with limited labeled data. Our experiments on air quality prediction and poverty mapping show that integrating proxy data implicitly through the location encoder outperforms using both as input to an observation encoder and fusion strategies that use frozen, pretrained location embeddings as a geographic prior. Superior performance for in-sample prediction shows that the PCL can incorporate rich information from the proxies, and superior out-of-sample prediction shows that the learned latent embeddings help generalize to areas without training labels.

Zhongying Wang, Kevin Lane, Levi Cai +2

University of Colorado, Boulder

Geospatial Representation LearningAir Quality PredictionMultimodal Fusion
AskPDF
Apr 20, 2026

DUALVISION: RGB-Infrared Multimodal Large Language Models for Robust Visual Reasoning

Multimodal large language models (MLLMs) have achieved impressive performance on visual perception and reasoning tasks with RGB imagery, yet they remain fragile under common degradations, such as fog, blur, or low-light conditions. Infrared (IR) imaging, a well-established complement to RGB, offers inherent robustness in these conditions, but its integration into MLLMs remains underexplored. To bridge this gap, we propose DUALVISION, a lightweight fusion module that efficiently incorporates IR-RGB information into MLLMs via patch-level localized cross-attention. To support training and evaluation and to facilitate future research, we also introduce DV-204K, a dataset of ~25K publicly available aligned IR-RGB image pairs with 204K modality-specific QA annotations, and DV-500, a benchmark of 500 IR-RGB image pairs with 500 QA pairs designed for evaluating cross-modal reasoning. Leveraging these datasets, we benchmark both open- and closed-source MLLMs and demonstrate that DUALVISION delivers strong empirical performance under a wide range of visual degradations. Our code and dataset are available at https://abrarmajeedi.github.io/dualvision.

Abrar Majeedi, Zhiyuan Ruan, Ziyi Zhao +3

University of Wisconsin-Madison · Amazon · Northeastern University

Cross-Modal LearningVisual Question AnsweringVLM RobustnessLarge Vision-Language ModelsMultimodal Large Language ModelsMultimodal Reasoning+2
AskPDF
Apr 19, 2026

DREAM: Dynamic Retinal Enhancement with Adaptive Multi-modal Fusion for Expert Precision Medical Report Generation

Automating medical reports for retinal images requires a sophisticated blend of visual pattern recognition and deep clinical knowledge. Current Large Vision-Language Models (LVLMs) often struggle in specialized medical fields where data is scarce, leading to models that overfit and miss subtle but critical pathologies. To address this, we introduce DREAM (Dynamic Retinal Enhancement with Adaptive Multi-modal Fusion), a novel framework for high-fidelity medical report generation that excels even with limited data. DREAM employs a unique two-stage fusion mechanism that intelligently integrates visual data with clinical keywords curated by ophthalmologists. First, the Abstractor module maps image and keyword features into a shared space, enhancing visual data with pathology-relevant insights. Next, the Adaptor performs adaptive multi-modal fusion, dynamically weighting the importance of each modality using learnable parameters to create a unified representation. To ensure the model's outputs are semantically grounded in clinical reality, a Contrastive Alignment module aligns these fused representations with ground-truth medical reports during training. By combining medical expertise with an efficient fusion strategy, DREAM sets a new state-of-the-art on the DeepEyeNet benchmark, achieving a BLEU-4 score of 0.241, and further demonstrates strong generalization to the ROCO dataset.

Nagur Shareef Shaik, Teja Krishna Cherukuri, Dong Hye Ye

Department of Computer Science, Georgia State University, Atlanta, GA USA

Medical ImagingMedical Report GenerationMedical VLMsMultimodal Fusion
AskPDF
Apr 18, 2026

Multimodal Fusion of Histopathology Images and Electronic Health Records for Early Breast Cancer Diagnosis

Breast cancer is a leading cause of cancer-related mortality worldwide, and timely accurate diagnosis is critical to improving survival outcomes. While convolutional neural networks (CNNs) have demonstrated strong performance on histopathology image classification, and machine learning models on structured electronic health records (EHR) have shown utility for clinical risk stratification, most existing work treats these modalities in isolation. This paper presents a systematic multimodal framework that integrates patch-level histopathology features from the BreCaHAD dataset with structured clinical data from MIMIC-IV. We train and evaluate unimodal image models (a simple CNN baseline and ResNet-18 with transfer learning), unimodal tabular models (XGBoost and a multilayer perceptron), and an intermediate-fusion model that concatenates latent representations from both modalities. ResNet-18 achieves near-perfect accuracy (1.000) and AUC (1.000) on three-class patch-level classification, while XGBoost achieves 98% accuracy on the EHR prediction task. The intermediate fusion model yields a macro-average AUC of 0.997, outperforming all unimodal baselines and delivering the largest improvements on the diagnostically critical but class-imbalanced mitosis category (AUC 0.994). Grad-CAM and SHAP interpretability analyses validate that model decisions align with established pathological and clinical criteria. Our results demonstrate that multimodal integration delivers meaningful improvements in both predictive performance and clinical transparency.

Aditya Shribhagwan Khandelwal, Mohammad Samar Ansari, Asra Aslam

University of Sheffield, UK · University of Chester, UK

Breast CancerComputational PathologyMultimodal ClassificationOncologyHistopathology Image ClassificationMultimodal Fusion
AskPDF
Apr 18, 2026

Dynamic Emotion and Personality Profiling for Multimodal Deception Detection

Deception detection is of great significance for ensuring information security and conducting public opinion analysis, with personality factors and emotion cues playing a critical role. However, existing methods lack sample-level dynamic annotations for emotions and personality.In this paper, we propose an innovative multi-model multi-prompt annotation scheme and a strict label quality evaluation standard, and establish a multimodal joint detection dataset DDEP for deception, emotion, and personality. Meanwhile, we propose Rel-DDEP, an adaptive reliability-weighted fusion framework. Our framework quantifies uncertainty by mapping modal features to a high-dimensional Gaussian distribution space. It then performs reliability-weighted fusion and incorporates an alignment module and a sorting constraint module to achieve joint detection of deception, emotion, and personality. Experimental results on the MDPE and DDEP datasets show that our Rel-DDEP significantly outperforms the existing state-of-the-art baseline models in three tasks. The F1 score of the deception detection increases by 2.53%, that of the emotion detection increases by 2.66%, and that of the personality detection increases by 9.30%. The experiments fully verify the necessity of annotating dynamic emotion and personality labels for each sample and the effectiveness of reliability-weighted fusion.

Li Zheng, Yanyi Luo, Hao Fei +5

Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China · National University of Singapore, Singapore, Singapore

Multimodal Emotion RecognitionUncertainty-Aware Multimodal FusionMultimodal Deception DetectionMultimodal Fusion
AskPDF
Apr 17, 2026

TriTS: Time Series Forecasting from a Multimodal Perspective

Time series forecasting plays a pivotal role in critical sectors such as finance, energy, transportation, and meteorology. However, Long-term Time Series Forecasting (LTSF) remains a significant challenge because real-world signals contain highly entangled temporal dynamics that are difficult to fully capture from a purely 1D perspective. To break this representation bottleneck, we propose TriTS, a novel cross-modal disentanglement framework that projects 1D time series into orthogonal time, frequency, and 2D-vision spaces.To seamlessly bridge the 1D-to-2D modality gap without the prohibitive O(N2)O(N^2) computational overhead of Vision Transformers (ViTs), we introduce a Period-Aware Reshaping strategy and incorporate Visual Mamba (Vim). This approach efficiently models cross-period dependencies as global visual textures while maintaining linear computational complexity. Complementing this, we design a Multi-Resolution Wavelet Mixing (MR-WM) module for the frequency modality, which explicitly decouples non-stationary signals into trend and noise components to achieve fine-grained time-frequency localization. Finally, a streaming linear branch is retained in the time domain to anchor numerical stability. By dynamically fusing these three complementary representations, TriTS effectively adapts to diverse data contexts. Extensive experiments across multiple benchmark datasets demonstrate that TriTS achieves state-of-the-art (SOTA) performance, fundamentally outperforming existing vision-based forecasters by drastically reducing both parameter count and inference latency.

Xiang Ao

School of Software Engineering, Beijing Jiaotong University Beijing 100044, China

Long-Term Time Series ForecastingCross-Modal Representation LearningNon-Stationary Time Series ForecastingMultimodal FusionMultiscale Time-Series Modeling
AskPDF
Apr 17, 2026

A Two-Stage Multi-Modal MRI Framework for Lifespan Brain Age Prediction

The accurate quantification of brain age from MRI has emerged as an important biomarker of brain health. However, existing approaches are often restricted to narrow age ranges and single-modality MRI data, limiting their capacity to capture the coordinated macro- and microstructural changes that unfold across the human lifespan. To address these limitations, we develop a multi-modal brain age framework to characterize the integrated evolution of brain morphology and white matter organization. Our model adopts a two-stage architecture, where modalities are processed independently and integrated via late fusion in both stages: first to estimate a probability distribution over six developmental stages, and then to predict age via probability-weighted stage-specialized experts. Experiments on nine datasets spanning fetal to elderly stages demonstrate competitive in-domain performance and out-of-domain generalization, with our method reducing MAE by 13% and 78% over existing baselines and multi-modal integration yielding 12-13% gains. Analysis of ADNI clinical groups further suggests the potential of the predicted brain age gap to characterize Alzheimer's-related brain aging.

Dingyi Zhang, Ruiying Liu, Yun Wang

Department of Computer Science, Emory University, Atlanta, GA, USA · Department of Biomedical Informatics, Emory University, Atlanta, GA, USA

Brain Age PredictionNeuroimagingMultimodal FusionBrain MRI
AskPDF
Apr 17, 2026

Information Router for Mitigating Modality Dominance in Vision-Language Models

Vision Language models (VLMs) have demonstrated strong performance across a wide range of benchmarks, yet they often suffer from modality dominance, where predictions rely disproportionately on a single modality. Prior approaches primarily address this issue by steering model's attention allocation, implicitly assuming that all modalities provide sufficient information. However, attention only determines where the model focuses, and cannot enrich information that is missing or ambiguous. In the real world, input modalities often differ in information density and their signal-to-noise ratios. In such cases, simply adjusting model's attention does not resolve the underlying lack of information. In this paper, we propose MoIR: Multi-modal Information Router, an information-level fusion method that explicitly reduces information disparity prior to fusion. MoIR identifies less informative tokens and routes complementary information from a stronger modality, constructing information-dense token representations before they are processed by a large language model. By modifying information availability, MoIR enables reliable shifts in modality dominance, even when one modality is degraded. We evaluate MoIR on three widely used multi-modal benchmarks across multiple model backbones. Experimental results show that MoIR consistently demonstrates more balanced modality contribution, and improves robustness and downstream performance, particularly even under modality degradation. These findings demonstrate that explicitly modifying cross-modal information is an effective and complementary strategy for mitigating modality dominance in multi-modal reasoning models.

Seulgi Kim, Mohit Prabhushankar, Ghassan AlRegib

OLIVES at the Center for Signal and Information Processing CSIP, School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA

VLM RobustnessVision-Language ModelsMultimodal Fusion
AskPDF
Apr 17, 2026

Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization

We propose HILBERT (HIerarchical Long-sequence Balanced Embedding with Reciprocal contrastive Training), a cross-attentive multimodal framework for learning document-level audio-text representations from long, segmented sequences in low-resource data settings. HILBERT leverages frozen pre-trained speech and language encoders to extract segment-level features, which are aggregated via cross-modal attention and self-attentive pooling to form modality-specific document representations and a joint cross-attentive embedding. To align modalities while preserving modality-specific structure under severe audio-text dimensional imbalance, we introduce a reciprocal dual contrastive objective that simultaneously aligns audio-to-joint and text-to-joint representations, rather than directly contrasting audio and text alone. Two auxiliary regularizers further stabilize long-sequence fusion: a Centered Kernel Alignment (CKA) loss that preserves structural consistency between each modality and the joint embedding, and a mutual information balancing loss that prevents dominance of a single modality by equalizing information flow from audio and text into the joint space. For downstream prediction, HILBERT employs a Mixture-of-Experts (MoE) classifier over concatenated audio, text, and joint representations to accommodate heterogeneous label regimes. Extensive evaluation across multiple audio-text backbone combinations demonstrates that HILBERT learns semantically meaningful long-sequence representations and achieves superior performance on highly imbalanced multi-class settings.

Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin

Dalhousie University, Halifax NS, Canada

Cross-Modal LearningModality ImbalanceCross-Modal AlignmentAudio UnderstandingAudio-Language ModelsMultimodal Classification+3
AskPDF
Apr 17, 2026

SWNet: A Cross-Spectral Network for Camouflaged Weed Detection

This paper presents SWNet, a bimodal end-to-end cross-spectral network specifically engineered for the detection of camouflaged weeds in dense agricultural environments. Plant camouflage, characterized by homochromatic blending where invasive species mimic the phenotypic traits of primary crops, poses a significant challenge for traditional computer vision systems. To overcome these limitations, SWNet utilizes a Pyramid Vision Transformer v2 backbone to capture long-range dependencies and a Bimodal Gated Fusion Module to dynamically integrate Visible and Near-Infrared information. By leveraging the physiological differences in chlorophyll reflectance captured in the NIR spectrum, the proposed architecture effectively discriminates targets that are otherwise indistinguishable in the visible range. Furthermore, an Edge-Aware Refinement module is employed to produce sharper object boundaries and reduce structural ambiguity. Experimental results on the Weeds-Banana dataset indicate that SWNet outperforms ten state-of-the-art methods. The study demonstrates that the integration of cross-spectral data and boundary-guided refinement is essential for high segmentation accuracy in complex crop canopies. The code is available on GitHub: https://cod-espol.github.io/SWNet/

Henry O. Velesaca, Luigi Miranda, Angel D. Sappa

ESPOL Polytechnic University, Campus Gustavo Galindo, 090902, Guayaquil, Ecuador · Software Engineering Department, Research Center for Information and Communication Technologies (CITIC-UGR), University of Granada, 18071, Granada, Spain · Computer Vision Center, Universitat Aut`onoma de Barcelona, 08193-Bellaterra, Barcelona, Spain

Agricultural Image AnalysisWeed DetectionMultispectral Object DetectionMultimodal FusionCamouflaged Object Detection
AskPDF
Apr 17, 2026

Dual-Modal Lung Cancer AI: Interpretable Radiology and Microscopy with Clinical Risk Integration

Lung cancer remains one of the leading causes of cancer-related mortality worldwide. Conventional computed tomography (CT) imaging, while essential for detection and staging, has limitations in distinguishing benign from malignant lesions and providing interpretable diagnostic insights. To address this challenge, this study proposes a dual-modal artificial intelligence framework that integrates CT radiology with hematoxylin and eosin (H&E) histopathology for lung cancer diagnosis and subtype classification. The system employs convolutional neural networks to extract radiologic and histopathologic features and incorporates clinical metadata to improve robustness. Predictions from both modalities are fused using a weighted decision-level integration mechanism to classify adenocarcinoma, squamous cell carcinoma, large cell carcinoma, small cell lung cancer, and normal tissue. Explainable AI techniques including Grad-CAM, Grad-CAM++, Integrated Gradients, Occlusion, Saliency Maps, and SmoothGrad are applied to provide visual interpretability. Experimental results show strong performance with accuracy up to 0.87, AUROC above 0.97, and macro F1-score of 0.88. Grad-CAM++ achieved the highest faithfulness and localization accuracy, demonstrating strong correspondence with expert-annotated tumor regions. These results indicate that multimodal fusion of radiology and histopathology can improve diagnostic performance while maintaining model transparency, suggesting potential for future clinical decision support systems in precision oncology.

Baramee Sukumal, Aueaphum Aueawatthanaphisut

Hatyaiwittayalai School, Hat Yai, Songkhla, Thailand, 90110 · School of Information, Computer, and Communication Technology,2026 Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand

Medical Image ClassificationExplainable Medical Image AnalysisHistopathology Image ClassificationMultimodal Fusion
AskPDF
Apr 17, 2026

EviDep: Uncertainty-Aware Multimodal Depression Estimation via Disentangled Evidential Learning

Audio--visual recordings provide complementary cues for estimating depression severity, but their informativeness varies across time and modalities. Point predictions alone do not express the uncertainty associated with these estimates. We present EviDep, a multimodal evidential regression framework that integrates multi-scale temporal modeling and shared--private representation learning for uncertainty-aware depression estimation. Frequency-aware Feature Extraction decomposes behavioral feature sequences into multiple frequency bands and refines them with scale-specific experts. Disentangled Evidential Learning encourages the disentanglement of cross-modal shared and modality-specific information in the refined features. Multi-branch Evidential Regression maps the resulting shared and private representations to three Normal-Inverse-Gamma (NIG) outputs and uses evidence-weighted aggregation to estimate depression severity and quantify aleatoric and epistemic uncertainty. Experiments on AVEC 2013, AVEC 2014, DAIC-WOZ, and E-DAIC show competitive prediction accuracy, with ablation studies supporting the contributions of frequency-aware refinement and shared--private disentanglement. Further analyses show that estimated epistemic uncertainty helps identify higher-error predictions, while both uncertainty estimates generally increase under controlled feature degradation.

Fangyuan Liu, Sirui Zhao, Yangsong Zhang +5

School of Computer Science and Technology, University of Science and Technology of China, Hefei, China · aSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, China · bSchool of Computer Science and Technology, Laboratory for Brain Science and Artificial Intelligence, Southwest University of Science and Technology, Mianyang, China +1

Disentangled Representation LearningEvidential Deep LearningDepression DetectionDepression Severity EstimationMultimodal FusionEpistemic Uncertainty
AskPDF
Apr 16, 2026

ExoNet: Calibrated Multimodal Deep Learning for TESS Exoplanet Candidate Vetting using Phase-Folded Light Curves, Stellar Parameters, and Multi-Head Attention

The discovery of exoplanets at scale has become one of the defining data science challenges in modern astrophysics. NASA's Transiting Exoplanet Survey Satellite (TESS) had catalogued over 7,800 planet candidates by early 2026, yet confirmation stands at fewer than 720. This paper introduces ExoNet, a multimodal deep learning framework that jointly processes phase-folded global and local light curve views alongside stellar parameter features through a calibrated late-fusion architecture combining 1D Convolutional Neural Networks, 8-head Multi-Head Attention over temporal feature maps, and a residual fusion head with post-hoc Temperature Scaling calibration. Trained on 7,585 labeled Kepler Objects of Interest, ExoNet achieves Test AUC = 0.9549 and 86.3% accuracy. Applied to 4,720 verified unconfirmed TESS Planet Candidates with TOI-TIC cross-identification verified against the NASA Exoplanet Archive, the model yields 1,754 high-confidence signals, 52 habitable-zone candidates, and six Earth-sized habitable-zone targets below 1.6 Earth radii. TOI-5728.01 and TOI-6716.01 emerge as the most Earth-like unconfirmed candidates. Full ablation confirms each modality improves AUC. Code and catalog are openly released.

Md. Rashadul Islam

Dept. of Computer Science and Engineering Daffodil International University Dhaka, Bangladesh

Time Series ClassificationAI-Assisted Scientific ResearchMultimodal FusionMulti-Head Attention
AskPDF
Apr 16, 2026

Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs

Omni-modal Large Language Models (Omni-MLLMs) are designed to reason over diverse sensory streams within a unified model. However, we find that multimodal reasoning is not solely determined by sensory evidence, but also by how modality information is organized. Through systematic analysis across diverse reasoning scenarios, we show that different modality organizations exhibit distinct advantages and limitations, and no single topology is universally optimal. Rather than proposing a general-purpose improvement to Omni-MLLM accuracy, we ask a narrower question: can these topology-induced failures be systematically identified and corrected? Motivated by this, we propose Chain of Modality (CoM), a framework that dynamically reorganizes multimodal topology during inference and learns adaptive organization strategies. Experiments across five benchmarks, diverse architectures, and model scales show that CoM reliably recovers topology-sensitive failures, through both training-free planning and lightweight Planner-SFT, while preserving performance on the full benchmark.

Ziyang Luo, Nian Liu, Junwei Han

Northwestern Polytechnical University Xi’an, Shaanxi, China

Multimodal Large Language ModelsMultimodal ReasoningMultimodal FusionMultimodal Understanding
AskPDF
Apr 15, 2026

M3R: Localized Rainfall Nowcasting with Meteorology-Informed MultiModal Attention

Accurate and timely rainfall nowcasting is crucial for disaster mitigation and water resource management. Despite recent advances in deep learning, precipitation prediction remains challenging due to limitations in effectively leveraging diverse multimedia data sources. We introduce M3R, a Meteorology-informed MultiModal attention-based architecture for direct Rainfall prediction that synergistically combines visual NEXRAD radar imagery with numerical Personal Weather Station (PWS) measurements, using a comprehensive pipeline for temporal alignment of heterogeneous meteorological data. With specialized multimodal attention mechanisms, M3R novelly leverages weather station time series as queries to selectively attend to spatial radar features, enabling focused extraction of precipitation signatures. Experimental results for three spatial areas of 100 km * 100 km centered at NEXRAD radar stations demonstrate that M3R outperforms existing approaches, achieving substantial improvements in accuracy, efficiency, and precipitation detection capabilities. Our work establishes new benchmarks for multimedia-based precipitation nowcasting and provides practical tools for operational weather prediction systems. The source code is available at https://github.com/Sanjeev97/M3Rain

Sanjeev Panta, Rhett M Morvant, Xu Yuan +2

University of Louisiana at Lafayette, Lafayette, LA, USA · University of Delaware, Newark, DE, USA

Precipitation NowcastingSpatiotemporal ForecastingMultimodal Fusion
AskPDF