Deep Multimodal Representation Learning from Temporal Data

The research progress in multimodal learning has grown rapidly over the last decade in several areas, especially in computer vision. The growing potential of multimodal data streams and deep learning algorithms has contributed to the increasing universality of deep multimodal learning. This involves the development of models capable of processing and analyzing the multimodal information uniformly. Unstructured real-world data can inherently take many forms, also known as modalities, often including visual and textual content. Extracting relevant patterns from this kind of data is still a motivating goal for researchers in deep learning. In this paper, we seek to improve the understanding of key concepts and algorithms of deep multimodal learning for the computer vision community by exploring how to generate deep models that consider the integration and combination of heterogeneous visual cues across sensory modalities. In particular, we summarize six perspectives from the current literature on deep multimodal learning, namely: multimodal data representation, multimodal fusion (i.e., both traditional and deep learning-based schemes), multitask learning, multimodal alignment, multimodal transfer learning, and zero-shot learning. We also survey current multimodal applications and present a collection of benchmark datasets for solving problems in various vision domains. Finally, we highlight the limitations and challenges of deep multimodal learning and provide insights and directions for future research.

This paper presents an approach for adaptive scheduling and robustness optimization in global logistics networks by integrating multimodal deep reinforcement learning with Internet of Things (IoT) technologies. We propose an integrated framework comprising a multimodal data fusion mechanism that synthesizes heterogeneous IoT sensor data, historical records, and contextual information; an adaptive deep reinforcement learning architecture that generates dynamic scheduling policies; and a multi-objective robust optimization method that balances operational efficiency with system resilience. The framework addresses key challenges in global logistics including demand volatility, transportation disruptions, and environmental uncertainties. Comprehensive experiments conducted on real-world logistics datasets demonstrate that our approach outperforms traditional methods with an 18.7% reduction in operational costs, 12.4% improvement in service levels, and significantly enhanced robustness under various disruption scenarios. The proposed method maintains 83% performance stability during complex disruptions compared to 51–72% for alternative approaches, while keeping computational requirements feasible for practical deployment. This research demonstrates potential contributions to AI-driven logistics operations management by showing improved supply chain performance through multimodal learning and robust optimization techniques.

4 - Deep multimodal representation learning for noninvasive neural speech decoding

BackgroundPathological complete response (pCR) to neoadjuvant systemic therapy (NAST) is an established prognostic marker in breast cancer (BC). Multimodal deep learning (DL), integrating diverse data sources (radiology, pathology, omics, clinical), holds promise for improving pCR prediction accuracy. This systematic review synthesizes evidence on multimodal DL for pCR prediction and compares its performance against unimodal DL.MethodsFollowing PRISMA, we searched PubMed, Embase, and Web of Science (January 2015–April 2025) for studies applying DL to predict pCR in BC patients receiving NAST, using data from radiology, digital pathology (DP), multi-omics, and/or clinical records, and reporting AUC. Data on study design, DL architectures, and performance (AUC) were extracted. A narrative synthesis was conducted due to heterogeneity.ResultsFifty-one studies, mostly retrospective (90.2%, median cohort 281), were included. Magnetic resonance imaging and DP were common primary modalities. Multimodal approaches were used in 52.9% of studies, often combining imaging with clinical data. Convolutional neural networks were the dominant architecture (88.2%). Longitudinal imaging improved prediction over baseline-only (median AUC 0.91 vs. 0.82). Overall, the median AUC across studies was 0.88, with 35.3% achieving AUC ≥ 0.90. Multimodal models showed a modest but consistent improvement over unimodal approaches (median AUC 0.88 vs. 0.83). Omics and clinical text were rarely primary DL inputs.ConclusionDL models demonstrate promising accuracy for pCR prediction, especially when integrating multiple modalities and longitudinal imaging. However, significant methodological heterogeneity, reliance on retrospective data, and limited external validation hinder clinical translation. Future research should prioritize prospective validation, integration underutilized data (multi-omics, clinical), and explainable AI to advance DL predictors to the clinical setting.

In recent years, deep learning technology has made breakthroughs in computer vision. After using large-scale data training, the deep neural network represented by GAN is significantly better than previous technologies in image generation, including generating more reasonable, higher-definition, more complex, and more accurate images. With the continuous development of datasets, models, and applications, the fusion of different modal information, including fusion of natural language, semantic layouts, tags, edge maps, and other different modal information, to generate images has become a new demand and challenge. There are related reviews on image generation and multimodal deep learning. However, there has not been a review dedicated to multimodal deep-learning image generation to discuss the current status, existing problems, and challenges of this task. Therefore, this review proposes a survey on multimodal deep learning image generation. It aims to provide readers with an application scenario for multimodal deep learning image generation. Also, it provides readers with new multimodal deep learning image generation technologies, the relevant datasets, evaluation metrics used, and some results comparison. Finally, this article describes some of the challenges and future topics of multimodal deep learning image generation.

The goal of multi-modal learning is to use complementary information on the relevant task provided by the multiple modalities to achieve reliable and robust performance. Recently, deep learning has led significant improvement in multi-modal learning by allowing for fusing high level features obtained at intermediate layers of the deep neural network. This paper addresses a problem of designing robust deep multi-modal learning architecture in the presence of the modalities degraded in quality. We introduce deep fusion architecture for object detection which processes each modality using the separate convolutional neural network (CNN) and constructs the joint feature maps by combining the intermediate features obtained by the CNNs. In order to facilitate the robustness to the degraded modalities, we employ the gated information fusion (GIF) network which weights the contribution from each modality according to the input feature maps to be fused. The combining weights are determined by applying the convolutional layers followed by the sigmoid function to the concatenated intermediate feature maps. The whole network including the CNN backbone and GIF is trained in an end-to-end fashion. Our experiments show that the proposed GIF network offers the additional architectural flexibility to achieve the robust performance in handling some degraded modalities.

Recent advances in data collecting methods have enabled life scientists to collect multimodal data from a variety of biological application fields. Multimodal deep learning is becoming more widespread as the capacity of multimodal data streams and deep learning algorithms grows. This leads to the creation of models capable of consistently processing and interpreting multimodal data. The fusion of multimodal data, such as genetic data and histopathological images, is important to better understand cancer heterogeneity and complexity for specific therapies, as well as improving predictions for cancer research. In this brief overview, we present several pioneering deep learning models where we focus on different architectures that has seen use in the medical field, shedding some light on the importance of deep learning in cancer diagnosis considering its immense results in recent years. We particularly set our eyes on multimodal deep learning approaches fusing histopathological images and genomic data to achieve better results than a single modality.

Objective:Poor outcomes in acute respiratory distress syndrome (ARDS) can be alleviated with tools that support early diagnosis. Current machine learning methods for detecting ARDS do not take full advantage of the multimodality of ARDS pathophysiology. We developed a multimodal deep learning model that uses imaging data, continuously collected ventilation data, and tabular data derived from a patient’s electronic health record (EHR) to make ARDS predictions.Materials and Methods:A chest radiograph (x-ray), at least two hours of ventilator waveform (VWD) data within the first 24 hours of intubation, and EHR-derived tabular data were used from 220 patients admitted to the ICU to train a deep learning model. The model uses pretrained encoders for the x-rays and ventilation data and trains a feature extractor on tabular data. Encoded features for a patient are combined to make a single ARDS prediction. Ablation studies for each modality assessed their effect on the model’s predictive capability.Results:The trimodal model achieved an area under the receiver operator curve (AUROC) of 0.86 with a 95% confidence interval of 0.01. This was a statistically significant improvement (p<0.05) over single modality models and bimodal models trained on VWD+tabular and VWD+x-ray data.Discussion and Conclusion:Our results demonstrate the potential utility of using deep learning to address complex conditions with heterogeneous data. More work is needed to determine the additive effect of modalities on ARDS detection. Our framework can serve as a blueprint for building performant multimodal deep learning models for conditions with small, heterogeneous datasets.

Preoperative Prediction of Axillary Lymph Node Metastasis in Patients With Breast Cancer Through Multimodal Deep Learning Based on Ultrasound and Magnetic Resonance Imaging Images

Real time forecasting of disasters needs to be advanced and easy because with increasing disasters their frequency and severity. Traditional prediction can only be made with traditional disaster prediction methods: numerical weather prediction (NWP) models and remote sensing techniques, which are computationally inefficient, data sparse and cannot adapt to dynamic environmental changes. In order to overcome these limitations, this research presents a Transformer Based Multimodal Deep Learning Model to combine the existing multiple data sources ranging from satellite imagery, IoT sensor networks, meteorological observations etc., to meteorological and social media analytics. The model employs a multimodal fusion strategy, enabling dynamic feature selection and seamless integration of heterogeneous data streams. In contrast to the conventional deep learning techniques, such as CNNs and LSTMs, the transformer based model has excellent ability towards long-range dependency, reducing the latency of light inference and better computational efficiency. The results are proven to be 94% accurate, 91% precise and has 40% reduction in inferencer latency in real time, which makes it suitable for disaster forecasting. The advancement of the multimodal deep learning methodologies presents this research as one which serves to contribute to the AI driven disaster resilience. We will also work on future work in the form of advanced transformer variants, more data integration, and explainable AI (XAI) techniques for model interpretability and scalability. Finding have implications for the transformative potential of AI in climate adaptation and serve as a robust foundation for the next generation early warning systems and climate adaptation disaster risk mitigation across multiple sectors.

As the fashion e-commerce markets rapidly develop, tens of thousands of products are registered daily on e-commerce platforms. Individual sellers register products after setting up a product category directly on a fashion e-commerce platform. However, many sellers fail to find a suitable category and mistakenly register their products under incorrect ones. Precise category matching is important for increasing sales through search optimization and accurate product exposure. However, manually correcting registered categories is time-consuming and costly for platform managers. To resolve this problem, this study proposes a methodology for fashion e-commerce product classification based on multi-modal deep learning and transfer learning. Through the proposed methodology, three challenges in classifying fashion e-commerce products are addressed. First, the issue of extremely biased e-commerce data is addressed through under-sampling. Second, multi-modal deep learning enables the model to simultaneously use input data in different formats, which helps mitigate the impact of noisy and low-quality e-commerce data by providing richer information.Finally, the high computational cost and long training times involved in training deep learning models with both image and text data are mitigated by leveraging transfer learning. In this study, three strategies for transfer learning to fine-tune the image and text modules are presented. In addition, five methods for fusing feature vectors extracted from a single modal into one and six strategies for fine-tuning multi-modal models are presented, featuring a total of 14 strategies. The study shows that multi-modal models outperform unimodal models based solely on text or image. It also suggests the optimal conditions for classifying e-commerce products, helping fashion e-commerce practitioners construct models tailored to their respective business environments more efficiently.

Performance of deep learning in mapping water quality of Lake Simcoe with long-term Landsat archive

Precision agriculture is a vital practice for improving the production of crops. The present work is aimed to develop a deep learning multimodal model that can predict the crop yield in Ecuadorian corn farms. The model takes multispectral images and field sensor data (humidity, temperature, or soil status) to obtain the yield of a crop. The use of multimodal data is aimed to extract hidden patterns in the status of crops and in this way obtain better results than the use of vegetation indices or other state-of-the-art methods. For the experiments, we utilized multi-spectral satellite images obtained from the google earth engine platform and monthly precipitation and temperature data of the 24 Ecuadorian provinces collected from the Ecuadorian Ministry of agriculture and livestock; likewise, we obtained the area of corn plantation in each province and their corn production for the years 2016 to 2020. Results indicate that the use of multimodal deep learning models (pre-trained CNN for images and LSTM for time series sensor data) gives better prediction accuracy than monomodal prediction models.KeywordsPrecision agricultureRemote sensingConvolutional neural networksRecurrent neural networksMultimodal deep learning

Due to the vital importance of promptly controlling plant diseases and the challenges facing today's agricultural disease management techniques, a novel framework has been introduced for detecting crop disease. This paper proposes a new methodology for detecting cotton leaf disease using multi-modal deep learning approaches. Since the early control of plant diseases is paramount and commonly utilized methods for managing agricultural diseases suffer in practice, a new framework for disease detection has been proposed. Inspecting modern deep learning algorithms concerning the analysis of images and processing for pattern recognition, we design a system utilizing visual indicators of diseases from multiple modalities to improve the detection of diseases in cotton leaves. We propose a new methodology utilizing deep learning algorithms that utilize spectral imagery, thermal imagery, and hyper-spectral images to merge their features and thus accurately identify plant diseases. This system allows measuring the plant’s general health to determine the type of disease symptoms occurring on the leaves of various cotton leaf trees in many environments. Hence, the outcomes of extensive experiments using multi-modal images of plants of various kinds – healthy and diseased – show that quantitative tests confirm the ability of the proposed system to detect different types of early cotton leaf diseases with an accuracy, sensitivity, and specificity equal to or better the results published in the literature, which allows the critical impact of the proposed multi-modal deep learning technique to give an early warning against plant diseases before it spreads in the fields, as well as the other numerous uses of its implementation and availability in agricultural papers and applications while aiding the reaching of the goals for further research and developments on the areas to be used by the governing territories where better scalable and accurate disease detection systems would be necessary for such large-scale agricultural needs and real-time surveillance applications.

Background: It is known that oral diseases such as periodontal (gum) disease are closely linked to various systemic diseases and disorders. Deep learning advances have the potential to make major contributions to healthcare, particularly in the domains that rely on medical imaging. Incorporating non-imaging information based on clinical and laboratory data may allow clinicians to make more comprehensive and accurate decisions. Methods: Here, we developed a multimodal deep learning method to predict systemic diseases and disorders from oral health conditions. A dual-loss autoencoder was used in the first phase to extract periodontal disease-related features from 1188 panoramic radiographs. Then, in the second phase, we fused the image features with the demographic data and clinical information taken from electronic health records (EHR) to predict systemic diseases. We used receiver operation characteristics (ROC) and accuracy to evaluate our model. The model was further validated by an unseen test dataset. Findings: According to our findings, the top three most accurately predicted chapters, in order, are the Chapters III, VI and IX. The results indicated that the proposed model could predict systemic diseases belonging to Chapters III, VI and IX, with AUC values of 0.92 (95% CI, 0.90-94), 0.87 (95% CI, 0.84-89) and 0.78 (95% CI, 0.75-81), respectively. To assess the robustness of the models, we performed the evaluation on the unseen test dataset for these chapters and the results showed an accuracy of 0.88, 0.82 and 0.72 for Chapters III, VI and IX, respectively. Interpretation: The present study shows that the combination of panoramic radiograph and clinical oral features could be considered to train a fusion deep learning model for predicting systemic diseases and disorders.