Multimodal Fusion

Sign Language Translation (SLT) is a challenging cross-modal task requiring joint modeling of manual articulations and non-manual signals. Existing gloss-free SLT methods effectively capture gestural dynamics but often underutilize facial expressions, which play crucial grammatical and disambiguating roles. This limitation can cause semantic degradation when distinct concepts share similar manual configurations. To address this issue, we propose FEA-SLT (Facial-Expression-Aware Sign Language Translation), a gloss-free end-to-end framework that uses facial dynamics to provide complementary cues to manual signals. FEA-SLT employs a domain-transferred facial encoder to extract expression-sensitive representations and integrates them with manual features through a linguistically motivated Facial-Expression-Aware Fusion (FEAF) module. FEAF captures reciprocal dependencies between manual and facial channels via bidirectional modulation, enhancing syntactic fidelity. Experiments on PHOENIX14T and CSL-Daily show that FEA-SLT achieves state-of-the-art BLEU performance among gloss-free methods, while targeted analyses support improved translation of facial-sensitive utterances. Code is available at https://github.com/TuGuobin/FEA-SLT.

Visual grounding (VG) localizes target objects in an image from natural-language expressions. In real-world perception, RGB cues often degrade under low illumination and adverse weather, making visual grounding substantially more challenging. However, existing VG benchmarks are largely RGB-only and provide limited, structured coverage of such conditions, hindering systematic robustness evaluation and cross-spectral comparison. We present RGBT-GroundBench, the first large-scale benchmark for RGB-Thermal (TIR) visual grounding in complex environments. It contains over 40K images (21,535 RGB-TIR pairs) and 38,760 object instances with referring expressions, bounding boxes, and fine-grained annotations at three levels: scene types, environmental conditions (illumination and weather), and object properties (size and occlusion). As a benchmark suite, RGBT-GroundBench provides not only curated RGB-TIR grounding annotations but also a unified evaluation protocol supporting RGB-only, TIR-only, and RGB+TIR inputs. Under this protocol, we benchmark 11 representative VG models across diverse scenes and environmental conditions. Our results show that grounding accuracy is strongly correlated with scene complexity, LoRA-based models are more robust in complex scenes, and low-illumination conditions cause significant performance degradation that has been rarely explored. Guided by these observations, we introduce RGBT-VGNet, a simple and reproducible reference baseline under the unified protocol, featuring Asymmetric Modality Adaptation, Language-Aware Visual Synergy, and Tri-Prior Fusion for reliability-aware RGB-TIR integration. Resources, annotations, code, checkpoints, and evaluation scripts have been publicly released.

Colonoscopic Polyp Re-Identification (ReID) aims to match the same polyp across a large gallery of images captured from different viewpoints and with different cameras, playing a critical role in computer-aided diagnosis for the prevention and treatment of colorectal cancer. However, the coarse granularity of high-level features often limits performance on small polyps, where fine-grained details are essential for accurate matching. To address this challenge, we propose a novel multimodal feature fusion architecture, termed the Gated Progressive Fusion Network, which selectively integrates features from multiple levels through fully connected gating mechanisms. Building on this framework, we introduce a gated progressive fusion strategy that enables layer-wise refinement of semantic information, facilitating multi-level feature interactions to enhance both generalization ability and robustness. Extensive experiments on standard benchmarks demonstrate the advantages of the multimodal setting over state-of-the-art unimodal ReID models, particularly when combined with the proposed fusion strategy tailored for general-purpose scenarios.

Understanding camera motion is a fundamental problem in embodied perception and 3D scene understanding. While visual methods have advanced rapidly, they often struggle under visually degraded conditions such as motion blur or occlusions. In this work, we show that passive scene sounds provide cues complementary to vision for relative camera pose estimation for in-the-wild videos. We introduce a simple but effective audio-visual framework that integrates direction-of-arrival (DOA) spectra and binauralized embeddings into a state-of-the-art vision-only pose estimation model. Our results on two large datasets show consistent gains over strong visual baselines, plus robustness when the visual information is corrupted. To our knowledge, this represents the first work to successfully leverage audio for relative camera pose estimation in real-world videos, and it establishes incidental, everyday audio as an unexpected but promising signal for a classic spatial challenge. Project: http://vision.cs.utexas.edu/projects/av_camera_pose.

Deep learning-based methods have achieved significant success in remote sensing Earth observation data analysis. Numerous feature fusion techniques address multimodal remote sensing image classification by integrating global and local features. However, these techniques often struggle to extract structural and detail features from heterogeneous and redundant multimodal images. With the goal of introducing frequency domain learning to model key and sparse detail features, this paper introduces the spatial-spectral-frequency interaction network (S$^2$Fin), which integrates pairwise fusion modules across the spatial, spectral, and frequency domains. Specifically, we propose a high-frequency sparse enhancement transformer that employs sparse spatial-spectral attention to optimize the parameters of the high-frequency filter. Subsequently, a two-level spatial-frequency fusion strategy is introduced, comprising an adaptive frequency channel module that fuses low-frequency structures with enhanced high-frequency details, and a high-frequency resonance mask that emphasizes sharp edges via phase similarity. In addition, a spatial-spectral attention fusion module further enhances feature extraction at intermediate layers of the network. Experiments on four benchmark multimodal datasets with limited labeled data demonstrate that S$^2$Fin performs superior classification, outperforming state-of-the-art methods. The code is available at https://github.com/HaoLiu-XDU/SSFin.

Audio-visual segmentation (AVS) plays a critical role in multimodal machine learning by effectively integrating audio and visual cues to precisely segment objects or regions within visual scenes. Recent AVS methods have demonstrated significant improvements. However, they overlook the inherent frequency-domain contradictions between audio and visual modalities--the substantial noise often present in audio high-frequency signals vs. the structurally rich details in visual high-frequency signals. Ignoring these differences can result in suboptimal performance. In this paper, we rethink the AVS task from a deeper perspective by reformulating AVS task as a frequency-domain decomposition and recomposition problem. To this end, we introduce a novel Frequency-Aware Audio-Visual Segmentation (FAVS) framework consisting of two key modules: Frequency-Domain Enhanced Decomposer (FDED) module and Synergistic Cross-Modal Consistency (SCMC) module. FDED module employs a residual-based iterative frequency decomposition to discriminate modality-specific semantics and structural features, and SCMC module leverages a mixture-of-experts architecture to reinforce semantic consistency and modality-specific feature preservation through dynamic expert routing. Extensive experiments demonstrate that our FAVS framework achieves state-of-the-art performance on three benchmark datasets, and abundant qualitative visualizations further verify the effectiveness of the proposed FDED and SCMC modules. The project repository is available at https://github.com/happylife-pk/FAVS.

Multi-label classification has broad applications and depends on powerful representations capable of capturing multiple interactions. We introduce Diff-Feat, a simple yet effective framework that extracts intermediate features from pre-trained diffusion-Transformer models for both images and text, and fuses them for downstream tasks. We observe distinct patterns in optimal feature selection: for vision tasks, the most discriminative intermediate feature along the diffusion process occurs at the middle step and is located at the middle block in Transformer. In contrast, for language tasks, the best feature occurs at the noise-free step and is located at the deepest block. Notably, a consistent phenomenon across diverse datasets: a fixed "Middle Layer" yields the best performance on various downstream classification tasks for images (under DiT-XL/2-256$\times$256 and various U-ViT architectures). We further analyze the underlying mechanism and its scaling behavior across model scales. To efficiently select representations, we devise a heuristic local-search algorithm that pinpoints the locally optimal "image-text"$\times$"block-timestep" pair among a few candidates, avoiding an exhaustive grid search. A simple fusion-linear projection followed by addition-of the selected representations achieves 46.1% mAP on Visual Genome 500 (with 500 categories) and 80.2% mAP on Pix2Cap-COCO (with 80 categories), consistently outperforming strong baseline methods. Code is available at https://github.com/lt-0123/Diff-Feat.

Pelvic fractures pose significant diagnostic challenges, particularly in cases where fracture signs are subtle or invisible on standard radiographs. To address this, we introduce PelFANet, a dual-stream attention network that fuses raw pelvic X-rays with segmented bone images to improve fracture classification. The network employs Fused Attention Blocks (FABlocks) to iteratively exchange and refine features from both inputs, capturing global context and localized anatomical detail. Trained in a two-stage pipeline with a segmentation-guided approach, PelFANet demonstrates superior performance over conventional methods. On the AMERI dataset, it achieves 88.68% accuracy and 0.9334 AUC on visible fractures, while generalizing effectively to invisible fracture cases with 82.29% accuracy and 0.8688 AUC, despite not being trained on them. These results highlight the clinical potential of anatomy-aware dual-input architectures for robust fracture detection, especially in scenarios with subtle radiographic presentations.

Current sign language translation (SLT) systems attempt to learn all aspects of signing---manual gestures, high-speed fingerspelling, and asynchronous non-manual facial cues---within a single end-to-end network. Learning multiple tasks without detailed supervision leads to poor recognition of fingerspelled proper nouns and technical terms, and leaves rich disambiguating information from lip movements largely unexploited. We introduce SignBind-LLM, a modular framework that addresses these limitations through three dedicated expert streams: one for continuous signing, one for fingerspelling, and one for lipreading. Each expert is pre-trained independently using CTC on approximately two million automatically generated pseudo-gloss sequences, removing the need for manual gloss annotation. A lightweight transformer with learned temporal alignment fuses the expert outputs, and a pre-trained language model translates the resulting pseudo-gloss sequences into fluent spoken English. At matched decoder scale (250M parameters), our architecture already surpasses all prior methods, confirming that the gains are architectural rather than a consequence of scaling the language model. Scaling to a larger decoder sets a new state-of-the-art across How2Sign: 23.1, BOBSL: 7.0, and ChicagoFSWild+: 73.6%, while requiring significantly lower training cost than prior approaches.

Early and accurate glaucoma detection is critical to prevent irreversible vision loss, yet existing AI methods often rely on unimodal inputs and lack interpretability. We present GlaBoost, a multimodal gradient boosting framework that unifies three complementary signals for glaucoma risk prediction: fundus image embeddings from a pretrained convolutional encoder,free-text neuroretinal rim assessments encoded by a transformer-based language model, and structured ophthalmic biomarkers. These modalities are fused into a single representation and classified by an enhanced XGBoost model.On two real-world annotated datasets, GlaBoost consistently outperforms unimodal and generic multimodal baselines. Feature importance analysis highlights the cup-to-disc ratio, rim thinning, and the ISNT rule as the dominant predictors, yielding clinically consistent and interpretable decisions. GlaBoost offers a transparent and scalable foundation for multimodal decision support in ophthalmology.

A recent line of research on spoken language assessment (SLA) employs neural models such as BERT and wav2vec 2.0 (W2V) to evaluate speaking proficiency across linguistic and acoustic modalities. Although both models effectively capture features relevant to oral competence, each exhibits modality-specific limitations. BERT-based methods rely on ASR transcripts, which often fail to capture prosodic and phonetic cues for SLA. In contrast, W2V-based methods excel at modeling acoustic features but lack semantic interpretability. To overcome these limitations, we propose a system that integrates W2V with Phi-4 multimodal large language model (MLLM) through a score fusion strategy. The proposed system achieves a root mean square error (RMSE) of 0.375 on the official test set of the Speak & Improve Challenge 2025, securing second place in the competition. For comparison, the RMSEs of the top-ranked, third-ranked, and official baseline systems are 0.364, 0.384, and 0.444, respectively.

We present the P$^3$ dataset, a large-scale multimodal benchmark for building vectorization, constructed from aerial LiDAR point clouds, high-resolution aerial imagery, and vectorized 2D building outlines, collected across three continents. The dataset contains over 10 billion LiDAR points with decimeter-level accuracy and RGB images at a ground sampling distance of 25 centimeter. While many existing datasets primarily focus on the image modality, P$^3$ offers a complementary perspective by also incorporating dense 3D information. We demonstrate that LiDAR point clouds serve as a robust modality for predicting building polygons, both in hybrid and end-to-end learning frameworks. Moreover, fusing aerial LiDAR and imagery further improves accuracy and geometric quality of predicted polygons. The P$^3$ dataset is publicly available, along with code and pretrained weights of three state-of-the-art models for building polygon prediction at https://github.com/raphaelsulzer/PixelsPointsPolygons .

Decoding language from the human brain remains a grand challenge for Brain-Computer Interfaces (BCIs). Current approaches typically rely on unimodal brain representations, neglecting the brain's inherently multimodal processing. Inspired by the brain's associative mechanisms, where viewing an image can evoke related sounds and linguistic representations, we propose a unified framework that leverages Multimodal Large Language Models (MLLMs) to align brain signals with a shared semantic space encompassing text, images, and audio. A router module dynamically selects and fuses modality-specific brain features according to the characteristics of each stimulus. Experiments on various fMRI datasets with textual, visual, and auditory stimuli demonstrate state-of-the-art performance, achieving an 8.48% improvement on the most commonly used benchmark. We further extend our framework to EEG and MEG data, demonstrating flexibility and robustness across varying temporal and spatial resolutions. To our knowledge, this is the first unified BCI architecture capable of robustly decoding multimodal brain activity across diverse brain signals and stimulus types, offering a flexible solution for real-world applications.

In this paper, we propose batch augmentation with unimodal fine-tuning for multimodal learning. We start with pre-trained unimodal models. We fine-tune the unimodal models with the application data. After that, we form a Multi-Layer Perceptron (MLP) head that takes information from unimodal models and provides output. Finally, we train the MLP layer and unimodal parts with batch augmentation. Depending on the data, some unimodal models can be replaced by hard-coded scripts or AI agents. The unimodal training can also follow batch augmentation when the data is augmentable. We write a multimodal batch augmentation dataloader script that implements the batch augmentation for the multimodal data. We investigate the proposed method on the FPU23 ultrasound and UPMC Food-101 multimodal datasets. The multimodal large language model (LLM) with the proposed training achieves the best average result among the investigated methods across both datasets. According to our literature search, the proposed method achieves state-of-the-art (SOTA) accuracy of 93.29% on the UPMC Food-101 dataset, while we apply the ViT-L/16 model for vision and the GPT-2 model for text. We share the scripts of the proposed method with traditional counterparts at the following repository: github.com/dipuk0506/multimodal

Most existing video anomaly detectors rely on RGB frames alone, which limit their ability to capture abrupt or transient motion cues that are critical for identifying anomalous events. We propose Uncertainty Weighted Image Event Fusion (IEF-VAD), a framework that integrates complementary RGB and synthetic motion information through a principled weighting mechanism. The method models the high variance and heavy tailed characteristics of synthetic motion cues with a Student's t likelihood, computes value level inverse variance weights using a Laplace approximation to prevent the image modality from overshadowing motion information, and performs iterative refinement to suppress residual cross modal noise. This formulation provides a more balanced and reliable fusion process compared to cross attention or gating based approaches that often suffer from modality dominance. Without requiring an event camera or frame level annotations, IEF-VAD achieves new state of the art performance on multiple real world anomaly detection benchmarks and remains stable under degradation applied to individual modalities. The results indicate that extracting and integrating complementary motion cues is an effective direction for robust video understanding across diverse environments.

Psychological evaluation relies on clinicians' observation and interpretation of a patient's emotional expression, which is susceptible to subjectivity, bias, fatigue, and inconsistency. This paper presents a multimodal emotion recognition system designed to support, rather than replace, the evaluator. The system combines facial expression recognition, speech emotion recognition, text-based emotion recognition of transcribed speech, and body movement analysis, and fuses their outputs into an emotional profile of class probabilities that is presented to the evaluator together with the overall prediction. Although the unimodal models achieve high accuracy on their benchmark test sets, a remote user study with 52 participants expressing seven emotional states shows that their accuracy falls to between 82.97% and 87.64% under realistic conditions, with individual emotional states recognised in as few as 48.08% of cases. Under the same conditions, the multimodal system achieves an accuracy of 96.43%, significantly higher than every single-modality component ($p < 10^{-4}$), with no emotional state below 92.31%. These results indicate that strong benchmark performance of a single channel does not transfer to realistic use, and that multimodal fusion provides the robustness required of a tool that supports psychological evaluation.

Existing brain tumor segmentation methods usually utilize multiple Magnetic Resonance Imaging (MRI) modalities in brain tumor images for segmentation, which can achieve better segmentation performance. However, in clinical applications, some modalities are often missing due to resource constraints, resulting in significant performance degradation for methods that rely on complete modality segmentation. In this paper, we propose a Multimodal feature distillation with Mamba-Transformer hybrid network (MMTSeg) for accurate brain tumor segmentation with missing modalities. We first employ a Multimodal Feature Distillation (MFD) module to distill feature-level multimodal knowledge into different unimodalities to extract complete modality information. We further develop an Unimodal Feature Enhancement (UFE) module to model the semantic relationship between global and local information. Finally, we built a Cross-Modal Fusion (CMF) module to explicitly align the global correlations across modalities, even when some modalities are missing. Complementary features within and across modalities are refined by the Mamba-Transformer hybrid architectures in both the UFE and CMF modules, dynamically capturing long-range dependencies and global semantic information for complex spatial contexts. A boundary-wise loss function is employed as the segmentation loss of the proposed MMTSeg to minimize boundary discrepancies for a distance-based metric. Our ablation study demonstrates the importance of the proposed feature enhancement and fusion modules in the proposed network and the Transformer with Mamba block for improving the performance of brain tumor segmentation with missing modalities. Extensive experiments on the BraTS 2018 and BraTS 2020 datasets demonstrate that the proposed MMTSeg framework outperforms state-of-the-art methods when modalities are missing.

Individuals with suspected rare genetic disorders often undergo multiple clinical evaluations, imaging studies, laboratory tests, and genetic tests over a prolonged period of time, a process commonly described as the diagnostic odyssey. Addressing this odyssey has substantial clinical, psychosocial, and economic benefits. Many rare genetic diseases have distinctive facial features that artificial intelligence algorithms can use to facilitate clinical diagnosis, to prioritize candidate diseases for further laboratory or genetic testing, and to support the phenotype-driven reinterpretation of genome or exome sequencing data. Existing methods that use frontal facial photographs were built on conventional convolutional neural networks, rely exclusively on facial images, and cannot capture non-facial phenotypic traits or demographic information that are essential for accurate diagnosis. Here we introduce GestaltMML, a multimodal machine learning approach based solely on the Transformer architecture. It integrates facial images, demographic information (age, sex, ethnicity), and clinical notes (optionally a list of Human Phenotype Ontology terms) to improve prediction accuracy. We evaluate GestaltMML on 528 diseases from the GestaltMatcher Database and on several in-house and published cohorts, including Beckwith-Wiedemann syndrome, Sotos syndrome, NAA10-related neurodevelopmental syndrome, Cornelia de Lange syndrome, and KBG syndrome. GestaltMML improves on the state-of-the-art image-only ensembled model, narrows the diagnostic accuracy gap for patients from under-represented ancestries, and clarifies when multimodal fusion is beneficial and when image-only inference is preferable. The results suggest that GestaltMML can greatly narrow the candidate diagnoses of rare diseases and may facilitate the reinterpretation of sequencing data.