Search

With the simultaneous acquisition of the infrared and optical remote sensing images of the same target becoming increasingly easy, using multi-modal data for high-performance object detection has become a research focus. In remote sensing multi-modal data, infrared images lack color information, it is hard to detect difficult targets with low contrast, and optical images are easily affected by illuminance. One of the most effective ways to solve this problem is to integrate multi-modal images for high-performance object detection. The challenge of fusion object detection lies in how to fully integrate multi-modal image features with significant modal differences and avoid introducing interference information while taking advantage of complementary advantages. To solve these problems, a new multi-modal fusion object detection method is proposed. In this paper, the method is improved in terms of two aspects: firstly, a new dual-branch asymmetric attention backbone network (DAAB) is designed, which uses a semantic information supplement module (SISM) and a detail information supplement module (DISM) to supplement and enhance infrared and RGB image information, respectively. Secondly, we propose a feature fusion pyramid network (FFPN), which uses a Transformer-like strategy to carry out multi-modal feature fusion and suppress features that are not conducive to fusion during the fusion process. This method is a state-of-the-art process for both FLIR-aligned and DroneVehicle datasets. Experiments show that this method has strong competitiveness and generalization performance. [ABSTRACT FROM AUTHOR]

Depth map super-resolution (DSR) is a technique aimed at restoring high-resolution (HR) depth maps from low-resolution (LR) depth maps. In this process, color images are commonly used as guidance to enhance the restoration procedure. However, the intricate degradation of LR depth poses a challenge, and previous image-guided DSR approaches, which implicitly model the degradation in the spatial domain, often fall short of producing satisfactory results. To address this challenge, we propose a novel approach called the Degradation-Guided Multi-modal Fusion Network (DMFNet). DMFNet explicitly characterizes the degradation and incorporates multi-modal fusion in both spatial and frequency domains to improve the depth quality. Specifically, we first introduce the deep degradation regularization loss function, which enables the model to learn the explicit degradation from the LR depth maps. Simultaneously, DMFNet converts the color images and depth maps into spectrum representations to provide comprehensive multi-domain guidance. Consequently, we present the multi-modal fusion block to restore the depth maps by leveraging both the RGB-D spectrum representations and the depth degradation. Extensive experiments demonstrate that DMFNet achieves state-of-the-art (SoTA) performance on four benchmarks, namely the NYU-v2, Middlebury, Lu, and RGB-D-D datasets. [ABSTRACT FROM AUTHOR]

Efficient flotation beneficiation heavily relies on accurate flotation condition recognition based on monitored froth video. However, the recognition accuracy is hindered by limitations of extracting temporal features from froth videos and establishing correlations between complex multi-modal high-order data. To address the difficulties of inadequate temporal feature extraction, inaccurate online condition detection, and inefficient flotation process operation, this paper proposes a novel flotation condition recognition method named the multi-modal temporal hypergraph neural network (MTHGNN) to extract and fuse multi-modal temporal features. To extract abundant dynamic texture features from froth images, the MTHGNN employs an enhanced version of the local binary pattern algorithm from three orthogonal planes (LBP-TOP) and incorporates additional features from the three-dimensional space as supplements. Furthermore, a novel multi-view temporal feature aggregation network (MVResNet) is introduced to extract temporal aggregation features from the froth image sequence. By constructing a temporal multi-modal hypergraph neural network, we encode complex high-order temporal features, establish robust associations between data structures, and flexibly model the features of froth image sequence, thus enabling accurate flotation condition identification through the fusion of multi-modal temporal features. The experimental results validate the effectiveness of the proposed method for flotation condition recognition, providing a foundation for optimizing flotation operations. [ABSTRACT FROM AUTHOR]

This paper introduces 'SkeletonCLIP++', an extension of our prior work in human action recognition, emphasizing the use of semantic information beyond traditional label-based methods. The innovation, 'Weighted Frame Integration' (WFI), shifts video feature computation from averaging to a weighted frame approach, enabling a more nuanced representation of human movements in line with semantic relevance. Another key development, 'Contrastive Sample Identification' (CSI), introduces a novel discriminative task within the model. This task involves identifying the most similar negative sample among positive ones, enhancing the model's ability to distinguish between closely related actions. Incorporating the 'BERT Text Encoder Integration' (BTEI) leverages the pre-trained BERT model as our text encoder to refine the model's performance. Empirical evaluations on HMDB-51, UCF-101, and NTU RGB+D 60 datasets illustrate positive improvements, especially in smaller datasets. 'SkeletonCLIP++' thus offers a refined approach to human action recognition, ensuring semantic integrity and detailed differentiation in video data analysis. [ABSTRACT FROM AUTHOR]

Objective: To comprehensively capture intra-tumor heterogeneity in head and neck cancer (HNC) and maximize the use of valid information collected in the clinical field, we propose a novel multi-modal image–text fusion strategy aimed at improving prognosis. Method: We have developed a tailored diagnostic algorithm for HNC, leveraging a deep learning-based model that integrates both image and clinical text information. For the image fusion part, we used the cross-attention mechanism to fuse the image information between PET and CT, and for the fusion of text and image, we used the Q-former architecture to fuse the text and image information. We also improved the traditional prognostic model by introducing time as a variable in the construction of the model, and finally obtained the corresponding prognostic results. Result: We assessed the efficacy of our methodology through the compilation of a multicenter dataset, achieving commendable outcomes in multicenter validations. Notably, our results for metastasis-free survival (MFS), recurrence-free survival (RFS), overall survival (OS), and progression-free survival (PFS) were as follows: 0.796, 0.626, 0.641, and 0.691. Our results demonstrate a notable superiority over the utilization of CT and PET independently, and exceed the result derived without the clinical textual information. Conclusions: Our model not only validates the effectiveness of multi-modal fusion in aiding diagnosis, but also provides insights for optimizing survival analysis. The study underscores the potential of our approach in enhancing prognosis and contributing to the advancement of personalized medicine in HNC. [ABSTRACT FROM AUTHOR]

Since camera and LiDAR sensors provide complementary information for the 3D semantic segmentation of intelligent vehicles, extensive efforts have been invested to fuse information from multi-modal data. Despite considerable advantages, fusion-based methods still have inevitable limitations: field-of-view disparity between two modal inputs, demanding precise paired data as inputs in both the training and inferring stages, and consuming more resources. These limitations pose significant obstacles to the practical application of fusion-based methods in real-world scenarios. Therefore, we propose a robust 3D semantic segmentation method based on multi-modal collaborative learning, aiming to enhance feature extraction and segmentation performance for point clouds. In practice, an attention based cross-modal knowledge distillation module is proposed to effectively acquire comprehensive information from multi-modal data and guide the pure point cloud network; then, a confidence-map-driven late fusion strategy is proposed to dynamically fuse the results of two modalities at the pixel-level to complement their advantages and further optimize segmentation results. The proposed method is evaluated on two public datasets (urban dataset SemanticKITTI and off-road dataset RELLIS-3D) and our unstructured test set. The experimental results demonstrate the competitiveness of state-of-the-art methods in diverse scenarios and a robustness to sensor faults. [ABSTRACT FROM AUTHOR]

High dynamic range imaging (HDRI) is an essential task in remote sensing, enhancing low dynamic range (LDR) remote sensing images and benefiting downstream tasks, such as object detection and image segmentation. However, conventional frame-based HDRI methods may encounter challenges in real-world scenarios due to the limited information inherent in a single image captured by conventional cameras. In this paper, an event-based remote sensing HDR imaging framework is proposed to address this problem, denoted as ERS-HDRI, which reconstructs the remote sensing HDR image from a single-exposure LDR image and its concurrent event streams. The proposed ERS-HDRI leverages a coarse-to-fine framework, incorporating the event-based dynamic range enhancement (E-DRE) network and the gradient-enhanced HDR reconstruction (G-HDRR) network. Specifically, to efficiently achieve dynamic range fusion from different domains, the E-DRE network is designed to extract the dynamic range features from LDR frames and events and perform intra- and cross-attention operations to adaptively fuse multi-modal data. A denoise network and a dense feature fusion network are then employed for the generation of the coarse, clean HDR image. Then, the G-HDRR network, with its gradient enhancement module and multiscale fusion module, performs structure enforcement on the coarse HDR image and generates a fine informative HDR image. In addition, this work introduces a specialized hybrid imaging system and a novel, real-world event-based remote sensing HDRI dataset that contains aligned remote sensing LDR images, remote sensing HDR images, and concurrent event streams for evaluation. Comprehensive experiments have demonstrated the effectiveness of the proposed method. Specifically, it improves state-of-the-art PSNR by about 30% and the SSIM score by about 9% on the real-world dataset. [ABSTRACT FROM AUTHOR]

Visual grounding aims to recognize and locate the target in the image according to human intention, which provides a new intelligent interaction idea and method for augmented reality (AR) and virtual reality (VR) devices. However, existing vision language grounding adopts language modals for visual grounding, but it performs ineffectively for images containing multiple similar objects. Gaze interaction is an important interaction mode in AR/VR devices, and it provides an advanced solution to the inaccurate vision language grounding cases. Based on the above questions and analysis, a vision language grounding framework fused with gaze intention is proposed. Firstly, we collect the manual gaze annotations using the AR device and construct a novel multi-modal dataset, RefCOCOg-Gaze, combining it with the proposed data augmentation methods. Secondly, an attention-based multi-modal feature fusion model is designed, providing a baseline framework for vision language grounding with gaze intention (VLG-Gaze). Through a series of precisely designed experiments, we analyze the proposed dataset and framework qualitatively and quantitatively. Comparing with the state-of-the-art vision language grounding model, our proposed scheme improves the accuracy by 5.3%, which indicates the significance of gaze fusion in multi-modal grounding tasks. [ABSTRACT FROM AUTHOR]

The accurate calculation of ore rock fragmentation is important for achieving the autonomous mining operation of mine excavators. However, a single mode cannot accurately calculate the ore rock fragmentation due to the low resolution of the point cloud mode and the lack of spatial position information of the image mode. To solve this problem, we propose an ore rock fragmentation calculation method (ORFCM) based on the multi-modal fusion of point clouds and images. The ORFCM makes full use of the advantages of multi-modal data, including the fine-grained object segmentation of images and spatial location information of point clouds. To solve the problem of image under-segmentation, we propose a multiscale adaptive edge-detection method based on an innovative standard deviation map to enhance the weak edges. Furthermore, an improved marked watershed segmentation algorithm is proposed to solve the problem of low segmentation accuracy caused by excessive noise of the gradient map and weak edges submerged. Experiments demonstrate that ORFCM can accurately calculate ore rock fragmentation in the local excavation area without relying on external markers for pixel calibration. The average error of the equivalent diameter of ore rock blocks is 0.66 cm, the average error of the elliptical long diameter is 1.42 cm, and the average error of the elliptical short diameter is 1.06 cm, which can effectively meet practical engineering needs. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs) are widely used in power transmission line inspection nowadays and they need to navigate automatically by recognizing the category and accurate position of transmission pylon equipment in line inspection. Semantic segmentation is an effective method for recognizing transmission pylon equipment. In this paper, a semantic segmentation algorithm that fuses infrared and natural light images is proposed. A cross-modal attention interaction activation mechanism is adopted to fully exploit the complementation between natural light and infrared images. Firstly, a global information block with a feature pyramid structure is used to deeply mine and fuse multi-scale global contextual information of fused features, and then the block is used to conduct feature aggregation in the decoding processing, and enough aggregation with multi-scale features of infrared and natural light images is used to enhance the expression ability of the model and improve the accuracy of semantic segmentation of transmission pylon equipment in complex scenes. Our method guides the process of low-level up-sampling and restoration by denser global and high-level features. Experimental results on a dataset of transmission pylon equipment collected by us show that the proposed method achieved better semantic segmentation results than the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The recently proposed spacecraft three-dimensional (3D) structure recovery method based on optical images and LIDAR has enhanced the working distance of a spacecraft's 3D perception system. However, the existing methods ignore the richness of temporal features and fail to capture the temporal coherence of consecutive frames. This paper proposes a sequential spacecraft depth completion network (S2DCNet) for generating accurate and temporally consistent depth prediction results, and it can fully exploit temporal–spatial coherence in sequential frames. Specifically, two parallel convolution neural network (CNN) branches were first adopted to extract the features latent in different inputs. The gray image features and the depth features were hierarchically encapsulated into unified feature representations through fusion modules. In the decoding stage, the convolutional long short-term memory (ConvLSTM) networks were embedded with the multi-scale scheme to capture the feature spatial–temporal distribution variation, which could reflect the past state and generate more accurate and temporally consistent depth maps. In addition, a large-scale dataset was constructed, and the experiments revealed the outstanding performance of the proposed S2DCNet, achieving a mean absolute error of 0.192 m within the region of interest. [ABSTRACT FROM AUTHOR]

As the number of modalities in biomedical data continues to increase, the significance of multi-modal data becomes evident in capturing complex relationships between biological processes, thereby complementing disease classification. However, the current multi-modal fusion methods for biomedical data require more effective exploitation of intra- and inter-modal interactions, and the application of powerful fusion methods to biomedical data is relatively rare. In this paper, we propose a novel multi-modal data fusion method that addresses these limitations. Our proposed method utilizes a graph neural network and a 3D convolutional network to identify intra-modal relationships. By doing so, we can extract meaningful features from each modality, preserving crucial information. To fuse information from different modalities, we employ the Low-rank Multi-modal Fusion method, which effectively integrates multiple modalities while reducing noise and redundancy. Additionally, our method incorporates the Cross-modal Transformer to automatically learn relationships between different modalities, facilitating enhanced information exchange and representation. We validate the effectiveness of our proposed method using lung CT imaging data and physiological and biochemical data obtained from patients diagnosed with Chronic Obstructive Pulmonary Disease (COPD). Our method demonstrates superior performance compared to various fusion methods and their variants in terms of disease classification accuracy. [ABSTRACT FROM AUTHOR]

Simple Summary: Contrast-enhanced MR has been used in diagnosing and treating liver patients. Recently, development in MR-guided radiation therapy calls for daily contrast MR for tumor targeting. However, frequent contrast injection is risky to patients. We developed a deep learning model (GRMM-GAN) to synthesize contrast-enhanced MR from pre-contrast images. GRMM-GAN adopts gradient regularization and multi-discrimination mechanisms. It shows superior performance compared with state-of-the-art deep learning models. Purposes: To provide abdominal contrast-enhanced MR image synthesis, we developed an gradient regularized multi-modal multi-discrimination sparse attention fusion generative adversarial network (GRMM-GAN) to avoid repeated contrast injections to patients and facilitate adaptive monitoring. Methods: With IRB approval, 165 abdominal MR studies from 61 liver cancer patients were retrospectively solicited from our institutional database. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast-enhanced (T1ce) images. The GRMM-GAN synthesis pipeline consists of a sparse attention fusion network, an image gradient regularizer (GR), and a generative adversarial network with multi-discrimination. The studies were randomly divided into 115 for training, 20 for validation, and 30 for testing. The two pre-contrast MR modalities, T2 and T1pre images, were adopted as inputs in the training phase. The T1ce image at the portal venous phase was used as an output. The synthesized T1ce images were compared with the ground truth T1ce images. The evaluation metrics include peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). A Turing test and experts' contours evaluated the image synthesis quality. Results: The proposed GRMM-GAN model achieved a PSNR of 28.56, an SSIM of 0.869, and an MSE of 83.27. The proposed model showed statistically significant improvements in all metrics tested with p-values < 0.05 over the state-of-the-art model comparisons. The average Turing test score was 52.33%, which is close to random guessing, supporting the model's effectiveness for clinical application. In the tumor-specific region analysis, the average tumor contrast-to-noise ratio (CNR) of the synthesized MR images was not statistically significant from the real MR images. The average DICE from real vs. synthetic images was 0.90 compared to the inter-operator DICE of 0.91. Conclusion: We demonstrated the function of a novel multi-modal MR image synthesis neural network GRMM-GAN for T1ce MR synthesis based on pre-contrast T1 and T2 MR images. GRMM-GAN shows promise for avoiding repeated contrast injections during radiation therapy treatment. [ABSTRACT FROM AUTHOR]

In autonomous driving, 3D object detection based on multi-modal data has become an indispensable perceptual approach when facing complex environments around the vehicle. During multi-modal detection, LiDAR and a camera are simultaneously applied for capturing and modeling. However, due to the intrinsic discrepancies between the LiDAR point and camera image, the fusion of the data for object detection encounters a series of problems, which results in most multi-modal detection methods performing worse than LiDAR-only methods. In this investigation, we propose a method named PTA-Det to improve the performance of multi-modal detection. Accompanied by PTA-Det, a Pseudo Point Cloud Generation Network is proposed, which can represent the textural and semantic features of keypoints in the image by pseudo points. Thereafter, through a transformer-based Point Fusion Transition (PFT) module, the features of LiDAR points and pseudo points from an image can be deeply fused under a unified point-based form. The combination of these modules can overcome the main obstacle of cross-modal feature fusion and achieves a complementary and discriminative representation for proposal generation. Extensive experiments on KITTI dataset support the effectiveness of PTA-Det, achieving a mAP (mean average precision) of 77.88% on the car category with relatively few LiDAR input points. [ABSTRACT FROM AUTHOR]

Membranous nephropathy is one of the most prevalent conditions responsible for nephrotic syndrome in adults. It is clinically nonspecific and mainly diagnosed by kidney biopsy pathology, with three prevalent techniques: light microscopy, electron microscopy, and immunofluorescence microscopy. Manual observation of glomeruli one by one under the microscope is very time-consuming, and there are certain differences in the observation results between physicians. This study makes use of whole-slide images scanned by a light microscope as well as immunofluorescence images to classify patients with membranous nephropathy. The framework mainly includes a glomerular segmentation module, a confidence coefficient extraction module, and a multi-modal fusion module. This framework first identifies and segments the glomerulus from whole-slide images and immunofluorescence images, and then a glomerular classifier is trained to extract the features of each glomerulus. The results are then combined to produce the final diagnosis. The results of the experiments show that the F1-score of image classification results obtained by combining two kinds of features, which can reach 97.32%, is higher than those obtained by using only light-microscopy-observed images or immunofluorescent images, which reach 92.76% and 93.20%, respectively. Experiments demonstrate that considering both WSIs and immunofluorescence images is effective in improving the diagnosis of membranous nephropathy. [ABSTRACT FROM AUTHOR]

Land cover mapping provides spatial information on the physical properties of the Earth's surface for various classes of wetlands, artificial surface and constructions, vineyards, water bodies, etc. Having reliable information on land cover is crucial to developing solutions to a variety of environmental problems, such as the destruction of important wetlands/forests, and loss of fish and wildlife habitats. This has made land cover mapping become one of the most widespread applications in remote sensing computational imaging. However, due to the differences between modalities in terms of resolutions, content, and sensors, integrating complementary information that multi-modal remote sensing imagery exhibits into a robust and accurate system still remains challenging, and classical segmentation approaches generally do not give satisfactory results for land cover mapping. In this paper, we propose a novel dynamic deep network architecture, AMM-FuseNet that promotes the use of multi-modal remote sensing images for the purpose of land cover mapping. The proposed network exploits the hybrid approach of the channel attention mechanism and densely connected atrous spatial pyramid pooling (DenseASPP). In the experimental analysis, in order to verify the validity of the proposed method, we test AMM-FuseNet with three datasets whilst comparing it to the six state-of-the-art models of DeepLabV3+, PSPNet, UNet, SegNet, DenseASPP, and DANet. In addition, we demonstrate the capability of AMM-FuseNet under minimal training supervision (reduced number of training samples) compared to the state of the art, achieving less accuracy loss, even for the case with 1/20 of the training samples. [ABSTRACT FROM AUTHOR]

Violence detection aims to locate violent content in video frames. Improving the accuracy of violence detection is of great importance for security. However, the current methods do not make full use of the multi-modal vision and audio information, which affects the accuracy of violence detection. We found that the violence detection accuracy of different kinds of videos is related to the change of optical flow. With this in mind, we propose an optical flow-aware-based multi-modal fusion network (OAMFN) for violence detection. Specifically, we use three different fusion strategies to fully integrate multi-modal features. First, the main branch concatenates RGB features and audio features and the optical flow branch concatenates optical flow features with RGB features and audio features, respectively. Then, the cross-modal information fusion module integrates the features of different combinations and applies weights to them to capture cross-modal information in audio and video. After that, the channel attention module extracts valuable information by weighting the integration features. Furthermore, an optical flow-aware-based score fusion strategy is introduced to fuse features of different modalities from two branches. Compared with methods on the XD-Violence dataset, our multi-modal fusion network yields APs that are 83.09% and 1.4% higher than those of the state-of-the-art methods in offline detection, and 78.09% and 4.42% higher than those of the state-of-the-art methods in online detection. [ABSTRACT FROM AUTHOR]

Dense depth perception is critical for many applications. However, LiDAR sensors can only provide sparse depth measurements. Therefore, completing the sparse LiDAR data becomes an important task. Due to the rich textural information of RGB images, researchers commonly use synchronized RGB images to guide this depth completion. However, most existing depth completion methods simply fuse LiDAR information with RGB image information through feature concatenation or element-wise addition. In view of this, this paper proposes a method to adaptively fuse the information from these two sensors by generating different convolutional kernels according to the content and positions of the feature vectors. Specifically, we divided the features into different blocks and utilized an attention network to generate a different kernel weight for each block. These kernels were then applied to fuse the multi-modal features. Using the KITTI depth completion dataset, our method outperformed the state-of-the-art FCFR-Net method by 0.01 for the inverse mean absolute error (iMAE) metric. Furthermore, our method achieved a good balance of runtime and accuracy, which would make our method more suitable for some real-time applications. [ABSTRACT FROM AUTHOR]

Featured Application: The proposed automatic depression detection method aims at: (1) supporting clinical diagnosis with objective and quantitative measurements and (2) providing a quick, effective, and economic self depressive assessment. Depression is a global mental health problem, the worst cases of which can lead to self-injury or suicide. An automatic depression detection system is of great help in facilitating clinical diagnosis and early intervention of depression. In this work, we propose a new automatic depression detection method utilizing speech signals and linguistic content from patient interviews. Specifically, the proposed method consists of three components, which include a Bidirectional Long Short-Term Memory (BiLSTM) network with an attention layer to deal with linguistic content, a One-Dimensional Convolutional Neural Network (1D CNN) to deal with speech signals, and a fully connected network integrating the outputs of the previous two models to assess the depressive state. Evaluated on two publicly available datasets, our method achieves state-of-the-art performance compared with the existing methods. In addition, our method utilizes audio and text features simultaneously. Therefore, it can get rid of the misleading information provided by the patients. As a conclusion, our method can automatically evaluate the depression state and does not require an expert to conduct the psychological evaluation on site. Our method greatly improves the detection accuracy, as well as the efficiency. [ABSTRACT FROM AUTHOR]

Gas supply system risk assessment is a serious and important problem in cities. Existing methods tend to manually build mathematical models to predict risk value from single-modal information, i.e., pipeline parameters. In this paper, we attempt to consider this problem from a deep-learning perspective and define a novel task, Urban Gas Supply System Risk Assessment (GSS-RA). To drive deep-learning techniques into this task, we collect and build a domain-specific dataset GSS-20K containing multi-modal data. Accompanying the dataset, we design a new deep-learning framework named GSS-RiskAsser to learn risk prediction. In our method, we design a parallel-transformers Vision Embedding Transformer (VET) and Score Matrix Transformer (SMT) to process multi-modal information, and then propose a Multi-Modal Fusion (MMF) module to fuse the features with a cross-attention mechanism. Experiments show that GSS-RiskAsser could work well on GSS-RA task and facilitate practical applications. Our data and code will be made publicly available. [ABSTRACT FROM AUTHOR]

Multi-modal fusion can achieve better predictions through the amalgamation of information from different modalities. To improve the performance of accuracy, a method based on Higher-order Orthogonal Iteration Decomposition and Projection (HOIDP) is proposed, in the fusion process, higher-order orthogonal iteration decomposition algorithm and factor matrix projection are used to remove redundant information duplicated inter-modal and produce fewer parameters with minimal information loss. The performance of the proposed method is verified by three different multi-modal datasets. The numerical results validate the accuracy of the performance of the proposed method having 0.4% to 4% improvement in sentiment analysis, 0.3% to 8% improvement in personality trait recognition, and 0.2% to 25% improvement in emotion recognition at three different multi-modal datasets compared with other 5 methods. [ABSTRACT FROM AUTHOR]

Vigilance estimation of drivers is a hot research field of current traffic safety. Wearable devices can monitor information regarding the driver's state in real time, which is then analyzed by a data analysis model to provide an estimation of vigilance. The accuracy of the data analysis model directly affects the effect of vigilance estimation. In this paper, we propose a deep coupling recurrent auto-encoder (DCRA) that combines electroencephalography (EEG) and electrooculography (EOG). This model uses a coupling layer to connect two single-modal auto-encoders to construct a joint objective loss function optimization model, which consists of single-modal loss and multi-modal loss. The single-modal loss is measured by Euclidean distance, and the multi-modal loss is measured by a Mahalanobis distance of metric learning, which can effectively reflect the distance between different modal data so that the distance between different modes can be described more accurately in the new feature space based on the metric matrix. In order to ensure gradient stability in the long sequence learning process, a multi-layer gated recurrent unit (GRU) auto-encoder model was adopted. The DCRA integrates data feature extraction and feature fusion. Relevant comparative experiments show that the DCRA is better than the single-modal method and the latest multi-modal fusion. The DCRA has a lower root mean square error (RMSE) and a higher Pearson correlation coefficient (PCC). [ABSTRACT FROM AUTHOR]

Facial expression recognition (FER) technology has made considerable progress with the rapid development of deep learning. However, conventional FER techniques are mainly designed and trained for videos that are artificially acquired in a limited environment, so they may not operate robustly on videos acquired in a wild environment suffering from varying illuminations and head poses. In order to solve this problem and improve the ultimate performance of FER, this paper proposes a new architecture that extends a state-of-the-art FER scheme and a multi-modal neural network that can effectively fuse image and landmark information. To this end, we propose three methods. To maximize the performance of the recurrent neural network (RNN) in the previous scheme, we first propose a frame substitution module that replaces the latent features of less important frames with those of important frames based on inter-frame correlation. Second, we propose a method for extracting facial landmark features based on the correlation between frames. Third, we propose a new multi-modal fusion method that effectively fuses video and facial landmark information at the feature level. By applying attention based on the characteristics of each modality to the features of the modality, novel fusion is achieved. Experimental results show that the proposed method provides remarkable performance, with 51.4% accuracy for the wild AFEW dataset, 98.5% accuracy for the CK+ dataset and 81.9% accuracy for the MMI dataset, outperforming the state-of-the-art networks. [ABSTRACT FROM AUTHOR]

The efficient multi-modal fusion of data streams from different sensors is a crucial ability that a robotic perception system should exhibit to ensure robustness against disturbances. However, as the volume and dimensionality of sensory-feedback increase it might be difficult to manually design a multimodal-data fusion system that can handle heterogeneous data. Nowadays, multi-modal machine learning is an emerging field with research focused mainly on analyzing vision and audio information. Although, from the robotics perspective, haptic sensations experienced from interaction with an environment are essential to successfully execute useful tasks. In our work, we compared four learning-based multi-modal fusion methods on three publicly available datasets containing haptic signals, images, and robots' poses. During tests, we considered three tasks involving such data, namely grasp outcome classification, texture recognition, and—most challenging—multi-label classification of haptic adjectives based on haptic and visual data. Conducted experiments were focused not only on the verification of the performance of each method but mainly on their robustness against data degradation. We focused on this aspect of multi-modal fusion, as it was rarely considered in the research papers, and such degradation of sensory feedback might occur during robot interaction with its environment. Additionally, we verified the usefulness of data augmentation to increase the robustness of the aforementioned data fusion methods. [ABSTRACT FROM AUTHOR]