Search Results (182)

Background/Objectives: This research investigates brain connectivity patterns in reaction to social and non-social stimuli within a virtual reality environment, emphasizing their impact on cognitive functions, specifically working memory. Methods: Employing the LEiDA framework with EEG data from 47 participants, I examined dynamic brain network states elicited by social avatars compared to non-social stick cues during a VR memory task. Through the integration of LEiDA with deep learning and graph theory analyses, unique connectivity patterns associated with cue type were discerned, underscoring the substantial influence of social cues on cognitive processes. LEiDA, conventionally utilized with fMRI, was creatively employed in EEG to detect swift alterations in brain network states, offering insights into cognitive processing dynamics. Results: The findings indicate distinct neural states for social and non-social cues; notably, social cues correlated with a unique brain state characterized by increased connectivity within self-referential and memory-processing networks, implying greater cognitive engagement. Moreover, deep learning attained approximately 99% accuracy in differentiating cue contexts, highlighting the efficacy of prominent eigenvectors from LEiDA in EEG analysis. Analysis of graph theory also uncovered structural network disparities, signifying enhanced integration in contexts involving social cues. Conclusions: This multi-method approach elucidates the dynamic influence of social cues on brain connectivity and cognition, establishing a basis for VR-based cognitive rehabilitation and immersive learning, wherein social signals may significantly enhance cognitive function. Full article

Attention deficit hyperactivity disorder (ADHD) is a prevalent neurodevelopmental disorder among children and adolescents. Behavioral detection and analysis play a crucial role in ADHD diagnosis and assessment by objectively quantifying hyperactivity and impulsivity symptoms. Existing video-based action recognition algorithms focus on object or interpersonal interactions, they may overlook ADHD-specific behaviors. Current keypoints-based algorithms, although effective in attenuating environmental interference, struggle to accurately model the sudden and irregular movements characteristic of ADHD children. This work proposes a novel keypoints-based system, the Multi-cue Feature Fusion Network (MF-Net), for recognizing actions and behaviors of children with ADHD during the Test of Variables of Attention (TOVA). The system aims to assess ADHD symptoms as described in the DSM-V by extracting features from human body and facial keypoints. For human body keypoints, we introduce the Multi-scale Features and Frame-Attention Adaptive Graph Convolutional Network (MSF-AGCN) to extract irregular and impulsive motion features. For facial keypoints, we transform data into images and employ MobileVitv2 for transfer learning to capture facial and head movement features. Ultimately, a feature fusion module is designed to fuse the features from both branches, yielding the final action category prediction. The system, evaluated on 3801 video samples of ADHD children, achieves 90.6% top-1 accuracy and 97.6% top-2 accuracy across six action categories. Additional validation experiments on public datasets NW-UCLA, NTU-2D, and AFEW-VA verify the network’s performance. Full article

The proliferation of AI-generated content (AIGC) has empowered non-experts to create highly realistic Deepfake images and videos using user-friendly software, posing significant challenges to the legal system, particularly in criminal investigations, court proceedings, and accident analyses. The absence of reliable Deepfake verification methods threatens the integrity of legal processes. In response, researchers have explored deep forgery detection, proposing various forensic techniques. However, the swift evolution of deep forgery creation and the limited generalizability of current detection methods impede practical application. We introduce a new deep forgery detection method that utilizes image decomposition and lighting inconsistency. By exploiting inherent discrepancies in imaging environments between genuine and fabricated images, this method extracts robust lighting cues and mitigates disturbances from environmental factors, revealing deeper-level alterations. A crucial element is the lighting information feature extractor, designed according to color constancy principles, to identify inconsistencies in lighting conditions. To address lighting variations, we employ a face material feature extractor using Pattern of Local Gravitational Force (PLGF), which selectively processes image patterns with defined convolutional masks to isolate and focus on reflectance coefficients, rich in textural details essential for forgery detection. Utilizing the Lambertian lighting model, we generate lighting direction vectors across frames to provide temporal context for detection. This framework processes RGB images, face reflectance maps, lighting features, and lighting direction vectors as multi-channel inputs, applying a cross-attention mechanism at the feature level to enhance detection accuracy and adaptability. Experimental results show that our proposed method performs exceptionally well and is widely applicable across multiple datasets, underscoring its importance in advancing deep forgery detection. Full article

The objective of 3D hand pose estimation (HPE) based on depth images is to accurately locate and predict keypoints of the hand. However, this task remains challenging because of the variations in hand appearance from different viewpoints and severe occlusions. To effectively address these challenges, this study introduces a novel approach, called the multi-perspective cue-aware joint relationship representation for 3D HPE via the Swin Transformer (MPCTrans, for short). This approach is designed to learn multi-perspective cues and essential information from hand depth images. To achieve this goal, three novel modules are proposed to utilize features from multiple virtual views of the hand, namely, the adaptive virtual multi-viewpoint (AVM), hierarchy feature estimation (HFE), and virtual viewpoint evaluation (VVE) modules. The AVM module adaptively adjusts the angles of the virtual viewpoint and learns the ideal virtual viewpoint to generate informative multiple virtual views. The HFE module estimates hand keypoints through hierarchical feature extraction. The VVE module evaluates virtual viewpoints by using chained high-level functions from the HFE module. Transformer is used as a backbone to extract the long-range semantic joint relationships in hand depth images. Extensive experiments demonstrate that the MPCTrans model achieves state-of-the-art performance on four challenging benchmark datasets. Full article

To address the challenges of suboptimal remote detection and significant computational burden in existing multi-sensor information fusion 3D object detection methods, a novel approach based on Bird’s-Eye View (BEV) is proposed. This method utilizes an enhanced lightweight EdgeNeXt feature extraction network, incorporating residual branches to address network degradation caused by the excessive depth of STDA encoding blocks. Meantime, deformable convolution is used to expand the receptive field and reduce computational complexity. The feature fusion module constructs a two-stage fusion network to optimize the fusion and alignment of multi-sensor features. This network aligns image features to supplement environmental information with point cloud features, thereby obtaining the final BEV features. Additionally, a Transformer decoder that emphasizes global spatial cues is employed to process the BEV feature sequence, enabling precise detection of distant small objects. Experimental results demonstrate that this method surpasses the baseline network, with improvements of 4.5% in the NuScenes detection score and 5.5% in average precision for detection objects. Finally, the model is converted and accelerated using TensorRT tools for deployment on mobile devices, achieving an inference time of 138 ms per frame on the Jetson Orin NX embedded platform, thus enabling real-time 3D object detection. Full article

Stimuli-responsive nanocomposite gels combine the unique properties of hydrogels with those of nanoparticles, thus avoiding the suboptimal results of single components and creating versatile, multi-functional platforms for therapeutic and diagnostic applications. These hybrid materials are engineered to respond to various internal and external stimuli, such as temperature, pH, light, magnetic fields, and enzymatic activity, allowing precise control over drug release, tissue regeneration, and biosensing. Their responsiveness to environmental cues permits personalized medicine approaches, providing dynamic control over therapeutic interventions and real-time diagnostic capabilities. This review explores recent advances in stimuli-responsive hybrid gels’ synthesis and application, including drug delivery, tissue engineering, and diagnostics. Overall, these platforms have significant clinical potential, and future research is expected to lead to unique solutions to address unmet medical needs. Full article

Accurate assessment of water surface velocity (WSV) is essential for flood prevention, disaster mitigation, and erosion control within hydrological monitoring. Existing image-based velocimetry techniques largely depend on correlation principles, requiring users to input and adjust parameters to achieve reliable results, which poses challenges for users lacking relevant expertise. This study presents RivVideoFlow, a user-friendly, rapid, and precise method for WSV. RivVideoFlow combines two-dimensional and three-dimensional orthorectification based on Ground Control Points (GCPs) with a deep learning-based multi-frame optical flow estimation algorithm named VideoFlow, which integrates temporal cues. The orthorectification process employs a homography matrix to convert images from various angles into a top-down view, aligning the image coordinates with actual geographical coordinates. VideoFlow achieves superior accuracy and strong dataset generalization compared to two-frame RAFT models due to its more effective capture of flow velocity continuity over time, leading to enhanced stability in velocity measurements. The algorithm has been validated on a flood simulation experimental platform, in outdoor settings, and with synthetic river videos. Results demonstrate that RivVideoFlow can robustly estimate surface velocity under various camera perspectives, enabling continuous real-time dynamic measurement of the entire flow field. Moreover, RivVideoFlow has demonstrated superior performance in low, medium, and high flow velocity scenarios, especially in high-velocity conditions where it achieves high measurement precision. This method provides a more effective solution for hydrological monitoring. Full article

In the realm of human–robot interaction, the integration of visual and verbal cues has become increasingly significant. This paper focuses on the challenges and advancements in referring image segmentation (RIS), a task that involves segmenting images based on textual descriptions. Traditional approaches to RIS have primarily focused on pixel-level classification. These methods, although effective, often overlook the interconnectedness of pixels, which can be crucial for interpreting complex visual scenes. Furthermore, while the PolyFormer model has shown impressive performance in RIS, its large number of parameters and high training data requirements pose significant challenges. These factors restrict its adaptability and optimization on standard consumer hardware, hindering further enhancements in subsequent research. Addressing these issues, our study introduces a novel two-branch decoder framework with SAM (segment anything model) for RIS. This framework incorporates an MLP decoder and a KAN decoder with a multi-scale feature fusion module, enhancing the model’s capacity to discern fine details within images. The framework’s robustness is further bolstered by an ensemble learning strategy that consolidates the insights from both the MLP and KAN decoder branches. More importantly, we collect the segmentation target edge coordinates and bounding box coordinates as input cues for the SAM model. This strategy leverages SAM’s zero-sample learning capabilities to refine and optimize the segmentation outcomes. Our experimental findings, based on the widely recognized RefCOCO, RefCOCO+, and RefCOCOg datasets, confirm the effectiveness of this method. The results not only achieve state-of-the-art (SOTA) performance in segmentation but are also supported by ablation studies that highlight the contributions of each component to the overall improvement in performance. Full article

As the core technology of artificial intelligence, salient object detection (SOD) is an important approach to improve the analysis efficiency of remote sensing images by intelligently identifying key areas in images. However, existing methods that rely on a single strategy, convolution or Transformer, exhibit certain limitations in complex remote sensing scenarios. Therefore, we developed a Dual-Stream Feature Collaboration Perception Network (DCPNet) to enable the collaborative work and feature complementation of Transformer and CNN. First, we adopted a dual-branch feature extractor with strong local bias and long-range dependence characteristics to perform multi-scale feature extraction from remote sensing images. Then, we presented a Multi-path Complementary-aware Interaction Module (MCIM) to refine and fuse the feature representations of salient targets from the global and local branches, achieving fine-grained fusion and interactive alignment of dual-branch features. Finally, we proposed a Feature Weighting Balance Module (FWBM) to balance global and local features, preventing the model from overemphasizing global information at the expense of local details or from inadequately mining global cues due to excessive focus on local information. Extensive experiments on the EORSSD and ORSSD datasets demonstrated that DCPNet outperformed the current 19 state-of-the-art methods. Full article

Prostate apoptosis response-4 (Par-4, also known as PAWR) is a ubiquitously expressed tumor suppressor protein that induces apoptosis selectively in cancer cells, while leaving normal cells unaffected. Our previous studies indicated that genetic loss of Par-4 promoted hepatic steatosis, adiposity, and insulin-resistance in chow-fed mice. Moreover, low plasma levels of Par-4 are associated with obesity in human subjects. The mechanisms underlying obesity in rodents and humans are multi-faceted, and those associated with adipogenesis can be functionally resolved in cell cultures. We therefore used pluripotent mouse embryonic fibroblasts (MEFs) or preadipocyte cell lines responsive to adipocyte differentiation cues to determine the potential role of Par-4 in adipocytes. We report that pluripotent MEFs from Par-4^−/− mice underwent rapid differentiation to mature adipocytes with an increase in lipid droplet accumulation relative to MEFs from Par-4^+/+ mice. Knockdown of Par-4 in 3T3-L1 pre-adipocyte cultures by RNA-interference induced rapid differentiation to mature adipocytes. Interestingly, basal expression of PPARγ, a master regulator of de novo lipid synthesis and adipogenesis, was induced during adipogenesis in the cell lines, and PPARγ induction and adipogenesis caused by Par-4 loss was reversed by replenishment of Par-4. Mechanistically, Par-4 downregulates PPARγ expression by directly binding to its upstream promoter, as judged by chromatin immunoprecipitation and luciferase-reporter studies. Thus, Par-4 transcriptionally suppresses the PPARγ promoter to regulate adipogenesis. Full article

Introduction: The co-circulation of COVID-19 and seasonal influenza highlighted the importance of promoting influenza vaccination. However, the influenza vaccination rate among the Chinese population is low and requires further promotion. This study examined multi-dimensional factors, such as knowledge of seasonal influenza, health perceptions, cues to action, patient–provider relationships, and COVID-19 pandemic-related factors, in relation to the uptake of the seasonal influenza vaccine (SIV) among the Chinese population. Methods: A cross-sectional, self-administered online survey using a quota sampling method was conducted among Chinese adults 18 years and older between June and August 2022. Multivariate logistic regression was performed to explore factors associated with the 2021 SIV behavior. Results: A total of 3161 individuals from different regions of China were included in this study. The multivariate logistic regression demonstrated that perceived severity of influenza, perceived barriers to taking SIV, cues to action, a stable relationship with providers, worry about contracting COVID-19 in immunization settings, non-pharmaceutical interventions (NPIs), and awareness of the influenza vaccine in protecting against COVID-19 were significantly associated with the SIV uptake. Conclusions: This study examined multi-dimensional factors that may influence SIV uptake. Health promotion programs should incorporate multi-dimensional factors, including personal and environmental factors, related to SIV promotion during the co-circulation period. Full article

The Great Wall, a pivotal part of Chinese cultural heritage listed on the World Heritage List since 1987, confronts challenges stemming from both natural deterioration and anthropogenic damage. Traditional conservation strategies are impeded by the Wall’s vast geographical spread, substantial costs, and the inefficiencies associated with conventional surveying techniques such as manual surveying, laser scanning, and low-altitude aerial photography. These methods often struggle to capture the Wall’s intricate details, resulting in limitations in field operations and practical applications. In this paper, we propose a novel framework utilizing depth cameras for the efficient real-time 3D reconstruction of the Great Wall. To overcome the challenge of the high complexity of reconstruction, we generate multi-level geometric features from raw depth images for hierarchical computation guidance. On one hand, the local set of sparse features serve as basic cues for multi-view-based reconstruction. On the other hand, the global set of dense features are employed for optimization guidance during reconstruction. The proposed framework facilitates the real-time, precise 3D reconstruction of the Great Wall in the wild, thereby significantly enhancing the capabilities of traditional surveying methods for the Great Wall. This framework offers a novel and efficient digital approach for the conservation and restoration of the Great Wall’s cultural heritage. Full article

The human trabecular meshwork (HTM) is responsible for regulating intraocular pressure (IOP) by means of gradient porosity. Changes in its physical properties, like increases in stiffness or alterations in the extracellular matrix (ECM), are associated with increases in the IOP, which is the primary cause of glaucoma. The complexity of its structure limits the engineered models to one-layered and simple approaches, which do not accurately replicate the biological and physiological cues related to glaucoma. Here, a combination of melt electrowriting (MEW) and solution electrospinning (SE) is explored as a biofabrication technique used to produce a gradient porous scaffold that mimics the multi-layered structure of the native HTM. Polycaprolactone (PCL) constructs with a height of 20–710 µm and fiber diameters of 0.7–37.5 µm were fabricated. After mechanical characterization, primary human trabecular meshwork cells (HTMCs) were seeded over the scaffolds within the subsequent 14–21 days. In order to validate the system’s responsiveness, cells were treated with dexamethasone (Dex) and the rho inhibitor Netarsudil (Net). Scanning electron microscopy and immunochemistry staining were performed to evaluate the expected morphological changes caused by the drugs. Cells in the engineered membranes exhibited an HTMC-like morphology and a correct drug response. Although this work demonstrates the utility of combining MEW and SE in reconstructing complex morphological features like the HTM, new geometries and dimensions should be tested, and future works need to be directed towards perfusion studies. Full article

Current multimodal neural machine translation (MNMT) approaches primarily focus on ensuring consistency between visual annotations and the source language, often overlooking the broader aspect of multimodal coherence, including target–visual and bilingual–visual alignment. In this paper, we propose a novel approach that effectively leverages target–visual consistency (TVC) and bilingual–visual consistency (BiVC) to improve MNMT performance. Our method leverages visual annotations depicting concepts across bilingual parallel sentences to enhance multimodal coherence in translation. We exploit target–visual harmony by extracting contextual cues from visual annotations during auto-regressive decoding, incorporating vital future context to improve target sentence representation. Additionally, we introduce a consistency loss promoting semantic congruence between bilingual sentence pairs and their visual annotations, fostering a tighter integration of textual and visual modalities. Extensive experiments on diverse multimodal translation datasets empirically demonstrate our approach’s effectiveness. This visually aware, data-driven framework opens exciting opportunities for intelligent learning, adaptive control, and robust distributed optimization of multi-agent systems in uncertain, complex environments. By seamlessly fusing multimodal data and machine learning, our method paves the way for novel control paradigms capable of effectively handling the dynamics and constraints of real-world multi-agent applications. Full article

The dimensional Yale Food Addiction Scale for Children 2.0 (dYFAS-C 2.0) was developed to provide a reliable psychometric measure for assessing food addiction in adolescents, in accordance with the updated addiction criteria proposed in the fifth edition of the Diagnostic and Statistical Manual (DSM-5). The present study aimed to evaluate the psychometric properties of the dYFAS-C 2.0 among Portuguese adolescents and pre-adolescents and to explore the relationship between food addiction and other eating behaviors such as grazing and intuitive eating. The participants were 131 Portuguese adolescents and pre-adolescents (53.4% female and 46.6% male) aged between 10 and 15 years (M_age = 11.8) and with a BMI between 11.3 and 35.3 (M_{BMI z-score} = 0.42). Confirmatory Factor Analysis demonstrated an adequate fit for the original one-factor model (χ² (104) = 182; p < 0.001; CFI = 0.97; TLI = 0.97; NFI = 0.94; SRMR = 0.101; RMSEA = 0.074; 95% CI [0.056; 0.091]). Food addiction was positively correlated with higher grazing (r = 0.69, p < 0.001) and negatively correlated with lower reliance on hunger/satiety cues (r = −0.22, p = 0.015). No significant association was found between food addiction and BMI z-score, or between food addiction and age. The results support the use of dYFAS-C 2.0 as a valid and reliable measure for assessing food addiction in Portuguese adolescents and pre-adolescents. Furthermore, the findings highlight that food addiction may be part of a spectrum of disordered eating behaviors associated with control impairment. Future research with a larger sample size could further elucidate the associations between food addiction and other variables, such as psychological distress and multi-impulsive spectrum behaviors. Full article