Search Results (897)

Person re-identification (ReID) refers to the task of retrieving target persons from image libraries captured by various distinct cameras. Over the years, person ReID has yielded favorable recognition outcomes under typical visible light conditions, yet there remains considerable scope for enhancement in challenging conditions. The challenges and research gaps include the following: multi-modal data fusion, semi-supervised and unsupervised learning, domain adaptation, ReID in 3D space, fast ReID, decentralized learning, and end-to-end systems. The main problems to be solved, which are the occlusion problem, viewpoint problem, illumination problem, background problem, resolution problem, openness problem, etc., remain challenges. For the first time, this paper uses person ReID in special scenarios as a basis for classification to categorize and analyze the related research in recent years. Starting from the perspectives of person ReID methods and research directions, we explore the current research status in special scenarios. In addition, this work conducts a detailed experimental comparison of person ReID methods employing deep learning, encompassing both system development and comparative methodologies. In addition, we offer a prospective analysis of forthcoming research approaches in person ReID and address unresolved concerns within the field. Full article

This study provides an in-depth analysis of GAF-Net, a novel model for video-based person re-identification (Re-ID) that matches individuals across different video sequences. GAF-Net combines appearance-based features with gait-based features derived from skeletal data, offering a new approach that diverges from traditional silhouette-based methods. We thoroughly examine each module of GAF-Net and explore various fusion methods at the both score and feature levels, extending beyond initial simple concatenation. Comprehensive evaluations on the iLIDS-VID and MARS datasets demonstrate GAF-Net’s effectiveness across scenarios. GAF-Net achieves state-of-the-art $93.2\%$ rank-1 accuracy on iLIDS-VID’s long sequences, while MARS results ($86.09\%$ mAP, $89.78\%$ rank-1) reveal challenges with shorter, variable sequences in complex real-world settings. We demonstrate that integrating skeleton-based gait features consistently improves Re-ID performance, particularly with long, more informative sequences. This research provides crucial insights into multi-modal feature integration in Re-ID tasks, laying a foundation for the advancement of multi-modal biometric systems for diverse computer vision applications. Full article

The deleterious health effects of prolonged sitting and physical inactivity are well-established, yet these behaviors are pervasive in modern culture. To inform interventions aimed at reducing sedentary behavior and increasing lifestyle activity, this study examined psychological and behavioral economic factors that may be associated with these behaviors. This cross-sectional study was conducted among 4072 adults in Israel. Participants completed a survey pertaining to lifestyle behaviors and economic preferences using an online platform in September 2020. The psychological and behavioral economic factors of interest were patience, self-control, risk-taking, grit, and general self-efficacy. Sedentary behavior and lifestyle activity (e.g., time spent moving about) was assessed using the Rapid Assessment Disuse Index (RADI) tool (higher score indicative of more sitting and less activity). Multivariable linear and logistic regression analyses examined the association between psychological and behavioral economic factors and RADI score. Among 4072 participants, those who were impatient (vs. patient, β: −1.13; 95% CI: −1.89, −0.38) had higher grit (β: −1.25, 95% CI: −1.73, −0.77), and those who were more risk-seeking (β: −0.23; 95% CI: −0.33, −0.13) had lower RADI scores (i.e., less sedentary, more active). Significant associations for grit and risk-taking were also observed when the RADI score was dichotomized, such that individuals who had higher grit or were more risk-seeking were more likely to be non-sedentary/active. No significant associations were observed for self-control or general self-efficacy. Higher grit and more risk-seeking were associated with a decreased propensity for sedentary behaviors and inactivity; these factors may provide targets for interventions aimed at reducing sedentary behavior and increasing lifestyle activity. Full article

In this work, we describe the design, manufacturing development, and refinement of a chemical detection platform designed to identify specific odorants in the natural gas industry. As the demand for reliable and sensitive volatile organic compound (VOC) detection systems is growing, our project aimed to construct multiple prototypes to enhance our detection capabilities and provide portable detection platforms. Throughout the development process across nominally identical and duplicated instruments, various failure modes were encountered, which provided insight into the design and manufacturing challenges present when designing such platforms. We conducted a post hoc root cause analysis for each failure mode, leading to a series of design modifications and solutions. This paper details these design and manufacturing challenges, the analytical methods used to diagnose and address them, and the resulting improvements in system performance. In the end, a debugging flow chart is presented to aid future researchers in solving the possible issues that could be encountered. Our findings show the complexities of bespoke chemical sensor design for unique applications and highlight the critical importance of iterative testing and problem-solving in the development of industrial detection technologies. Achieving consistency across devices is essential for optimizing device-to-device efficiency. The work presented is the first step towards ensuring uniform performance across a production run of chemically sensitive devices. In the future, a universal device calibration model will be implemented, eliminating the need to collect data from each individual device. Full article

Modern aquaculture utilizes computer vision technology to analyze underwater images of fish, contributing to optimized water quality and improved production efficiency. The purpose of this study is to efficiently perform underwater fish detection and tracking using multi-object tracking (MOT) technology. To achieve this, the FairMOT model was employed to simultaneously implement pixel-level object detection and re-identification (Re-ID) functions, comparing two backbone models: FairMOT+YOLOv5s and FairMOT+DLA-34. The study constructed a dataset targeting the popular black porgy in Korean aquaculture, using underwater video data from five different environments collected from the internet. During the training process, the FairMOT+YOLOv5s model rapidly reduced train loss and demonstrated stable performance. The FairMOT+DLA-34 model showed better results in ID tracking performance, with an accuracy of 44.1%, an IDF1 of 11.0%, an MOTP of 0.393, and an IDSW of 1. In contrast, the FairMOT+YOLOv5s model recorded an accuracy of 43.8%, an IDF1 of 14.6%, an MOTP of 0.400, and an IDSW of 10. The results of this study indicate that the FairMOT+YOLOv5s model demonstrated higher IDF1 and MOTP scores compared to the FairMOT+DLA-34 model, while the FairMOT+DLA-34 model showed superior performance in ID tracking accuracy and had fewer ID switches. Full article

To further investigate the inhibition of Pseudomonas aeruginosa’s in vitro growth and biofilm formation by an organo-selenium-incorporated polyurethane (PU) catheter material. P. aeruginosa, Staphylococcus aureus, and Candida albicans were incubated in vitro with organo-selenium and control polyurethane catheter materials in the presence of glutathione. Growth was evaluated by a colony-forming-unit (CFU) count and visualized with confocal laser scanning microscopy. Two different PU catheter materials were used. Using tin-catalyzed PU catheter material, complete inhibition of S. aureus was seen at 1% selenium (Se), whereas no inhibition was seen for P. aeruginosa at up to 3.0% Se. Whereas, using a thermoplastic PU catheter material, 1.5% Se and 2% Se organo-selenium caused several logs of growth inhibition of P. aeruginosa, and 2.5% selenium, incorporation showed complete inhibition (8 logs). Samples with lower than 1.5% selenium did not show adequate growth inhibition for P. aeruginosa. Similar in vitro growth inhibition was achieved against a multidrug-resistant C. albicans strain. It was concluded that optimal inhibition of P. aeruginosa in vitro growth and biofilm formation occurs with 2.5% selenium incorporated as organo-selenium in a thermoplastic PU catheter material. These results suggest that reduced incidence of CAUTIs (catheter associated urinary tract infections) with P. aeruginosa and other bacteria and fungi can be achieved by using organo-selenium-incorporated catheters. Full article

The transition from wakefulness to sleep occurs when the core body temperature decreases. The latter is facilitated by an increase in the cutaneous blood flow, which dissipates internal heat into the micro-environment surrounding the sleeper’s body. The rise in cutaneous blood flow near sleep onset causes the distal (hands and feet) and proximal (abdomen) temperatures to increase by about 1 °C and 0.5 °C, respectively. Characterizing the dynamics of skin temperature changes throughout sleep phases and understanding its relationship with sleep quality requires a means to unobtrusively and longitudinally estimate the skin temperature. Leveraging the data from a temperature sensor strip (TSS) with five individual temperature sensors embedded near the surface of a smart bed’s mattress, we have developed an algorithm to estimate the distal skin temperature with a minute-long temporal resolution. The data from 18 participants who recorded TSS and ground-truth temperature data from sleep during 14 nights at home and 2 nights in a lab were used to develop an algorithm that uses a two-stage regression model (gradient boosted tree followed by a random forest) to estimate the distal skin temperature. A five-fold cross-validation procedure was applied to train and validate the model such that the data from a participant could only be either in the training or validation set but not in both. The algorithm verification was performed with the in-lab data. The algorithm presented in this research can estimate the distal skin temperature at a minute-level resolution, with accuracy characterized by the mean limits of agreement [−0.79 to +0.79 °C] and mean coefficient of determination $R^2=0.87$. This method may enable the unobtrusive, longitudinal and ecologically valid collection of distal skin temperature values during sleep. Therelatively small sample size motivates the need for further validation efforts. Full article

Three-dimensional multi-object tracking (MOT) using lidar point cloud data is crucial for applications in autonomous driving, smart cities, and robotic navigation. It involves identifying objects in point cloud sequence data and consistently assigning unique identities to them throughout the sequence. Occlusions can lead to missed detections, resulting in incorrect data associations and ID switches. To address these challenges, we propose a novel point cloud multi-object tracker called GBRTracker. Our method integrates an intra-frame graph structure into the backbone to extract and aggregate spatial neighborhood node features, significantly reducing detection misses. We construct an inter-frame bipartite graph for data association and design a sophisticated cost matrix based on the center, box size, velocity, and heading angle. Using a minimum-cost flow algorithm to achieve globally optimal matching, thereby reducing ID switches. For unmatched detections, we design a motion-based re-identification (ReID) feature embedding module, which uses velocity and the heading angle to calculate similarity and association probability, reconnecting them with their corresponding trajectory IDs or initializing new tracks. Our method maintains high accuracy and reliability, significantly reducing ID switches and trajectory fragmentation, even in challenging scenarios. We validate the effectiveness of GBRTracker through comparative and ablation experiments on the NuScenes and Waymo Open Datasets, demonstrating its superiority over state-of-the-art methods. Full article

SARS-CoV-2, the causative agent of the COVID-19 pandemic, has had a global impact, affecting millions over the last three years. Pre-existing lung diseases adversely affect the prognosis of infected COVID-19 patients, and agricultural workers routinely exposed to inhalable organic dusts have substantial increased risk for developing chronic lung diseases. In previous studies, we characterized the protein kinase C (PKC)-dependent airway inflammation mediated by organic dust extract (ODE) derived from dust collected from swine confinement facilities in in vitro and in vivo models. Here, we studied the effect of ODE on SARS-CoV-2 pseudoviral infection in mice and human bronchial epithelial cells (BEAS-2B). In wild-type (WT) and transgenic mice expressing the human angiotensin I-converting enzyme 2 (ACE2) receptor (SARS-CoV-2 entry receptor), ODE increased ACE2 shedding by ADAM-17 in the lungs. After repeated ODE treatments, the increased soluble ACE2 correlated to higher pseudovirus titer in the mouse lungs. In the human bronchial epithelial cells, ODE augmented PKCα activity in WT cells, and membrane ACE2 expression was diminished in PKCα-dominant negative cells. Unlike in the mice, increasing membrane ACE2 levels by treating with PKCα or ADAM-17 inhibitors and a low dose of ODE enhanced pseudoviral entry in vitro. Following viral entry, IL-8 secretion by the cells was diminished in a PKCα- and ADAM-17-independent manner. Together, the complex mechanisms involved in the synergistic effects of agricultural dust and SARS-CoV-2 highlight the importance of studying dust-mediated changes to immunity against circulating pathogens. Full article

The visible-infrared person re-identification (VI-ReID) task aims to retrieve the same pedestrian between visible and infrared images. VI-ReID is a challenging task due to the huge modality discrepancy and complex intra-modality variations. Existing works mainly complete the modality alignment at one stage. However, aligning modalities at different stages has positive effects on the intra-class and inter-class distances of cross-modality features, which are often ignored. Moreover, discriminative features with identity information may be corrupted in the processing of modality alignment, further degrading the performance of person re-identification. In this paper, we propose a progressive discriminative feature learning (PDFL) network that adopts different alignment strategies at different stages to alleviate the discrepancy and learn discriminative features progressively. Specifically, we first design an adaptive cross fusion module (ACFM) to learn the identity-relevant features via modality alignment with channel-level attention. For well preserving identity information, we propose a dual-attention-guided instance normalization module (DINM), which can well guide instance normalization to align two modalities into a unified feature space through channel and spatial information embedding. Finally, we generate multiple part features of a person to mine subtle differences. Multi-loss optimization is imposed during the training process for more effective learning supervision. Extensive experiments on the public datasets of SYSU-MM01 and RegDB validate that our proposed method performs favorably against most state-of-the-art methods. Full article

Multi-modal object re-identification (ReID) is a challenging task that seeks to identify objects across different image modalities by leveraging their complementary information. Traditional CNN-based methods are constrained by limited receptive fields, whereas Transformer-based approaches are hindered by high computational demands and a lack of convolutional biases. To overcome these limitations, we propose a novel fusion framework named MambaReID, integrating the strengths of both architectures with the effective VMamba. Specifically, our MambaReID consists of three components: Three-Stage VMamba (TSV), Dense Mamba (DM), and Consistent VMamba Fusion (CVF). TSV efficiently captures global context information and local details with low computational complexity. DM enhances feature discriminability by fully integrating inter-modality information with shallow and deep features through dense connections. Additionally, with well-aligned multi-modal images, CVF provides more granular modal aggregation, thereby improving feature robustness. The MambaReID framework, with its innovative components, not only achieves superior performance in multi-modal object ReID tasks, but also does so with fewer parameters and lower computational costs. Our proposed MambaReID’s effectiveness is validated by extensive experiments conducted on three multi-modal object ReID benchmarks. Full article

In January 2020, increased mortality was reported in a small broiler breeder flock in County Fermanagh, Northern Ireland. Gross pathological findings included coelomitis, oophoritis, salpingitis, visceral gout, splenomegaly, and renomegaly. Clinical presentation included inappetence, pronounced diarrhoea, and increased egg deformation. These signs, in combination with increased mortality, triggered a notifiable avian disease investigation. High pathogenicity avian influenza virus (HPAIV) was not suspected, as mortality levels and clinical signs were not consistent with HPAIV. Laboratory investigation demonstrated the causative agent to be a low-pathogenicity avian influenza virus (LPAIV), subtype H6N1, resulting in an outbreak that affected 15 premises in Northern Ireland. The H6N1 virus was also associated with infection on 13 premises in the Republic of Ireland and six in Great Britain. The close genetic relationship between the viruses in Ireland and Northern Ireland suggested a direct causal link whereas those in Great Britain were associated with exposure to a common ancestral virus. Overall, this rapidly spreading outbreak required the culling of over 2 million birds across the United Kingdom and the Republic of Ireland to stamp out the incursion. This report demonstrates the importance of investigating LPAIV outbreaks promptly, given their substantial economic impacts. Full article

Background: Severe combined immunodeficiency (SCID) is a life-threatening genetic disorder caused by critical defects of the immune system. Almost all cases are lethal if not treated within the first two years of life. Early diagnosis and intervention are thus essential for improving patient outcomes. In 2013, Ontario became the first Canadian province to perform newborn screening (NBS) for SCID by T cell receptor excision circles (TRECs) analysis, a surrogate marker of thymic function and lymphocyte maturation. Methods: This retrospective study reports on nearly 10 years of NBS for SCID at a quaternary referral centre. Results: From August 2013 to April 2023, our centre’s densely populated catchment area flagged 162 newborns with low TRECs levels, including 10 cases with SCID. Follow-up revealed other causes of low TRECs, including non-SCID T cell lymphopenia (secondary/reversible or idiopathic causes, and syndromic conditions) and prematurity. A small number of cases with normal repeat TRECs levels and/or T cell subsets were also flagged. Province-wide data from around this period revealed at least 24 diagnosed cases of SCID or Leaky SCID. Conclusions: This is the first report of NBS outcomes in a Canadian province describing the causative genetic defects, and the non-SCID causes of a positive NBS for SCID. Full article

Human papillomavirus (HPV) infection poses a significant health challenge, particularly in low- and middle-income countries (LMIC), where limited healthcare access and awareness hinder vaccine accessibility. To identify alternative HPV targeting interventions, we previously reported on surfactant protein A (SP-A) as a novel molecule capable of recognising HPV16 pseudovirions (HPV16-PsVs) and reducing infection in a murine cervicovaginal HPV challenge model. Building on these findings, our current study aimed to assess SP-A’s suitability as a broad-spectrum HPV-targeting molecule and its impact on innate immune responses. We demonstrate SP-A’s ability to agglutinate and opsonise multiple oncogenic HPV-PsVs types, enhancing their uptake and clearance by RAW264.7 murine macrophages and THP-1 human-derived immune cells. The SP-A opsonisation of HPV not only led to increased lysosomal accumulation in macrophages and HaCaT keratinocytes but also resulted in a decreased infection of HaCaT cells, which was further decreased when co-cultured with innate immune cells. An analysis of human innate immune cell cytokine profiles revealed a significant inflammatory response upon SP-A exposure, potentially contributing to the overall inhibition of HPV infection. These results highlight the multi-layered impact of SP-A on HPV, innate immune cells and keratinocytes and lay the basis for the development of alternative prophylactic interventions against diverse HPV types. Full article

Tuberculosis (TB) is the leading cause of death among people with HIV-1 infection. To improve the diagnosis and treatment of HIV-TB patients, it is important to understand the mechanisms underlying these conditions. Here, we used an integrated genomics approach to analyze and determine the lncRNAs that are dysregulated in HIV-TB patients and HIV-TB patients undergoing anti-retroviral therapy (ART) using a dataset available in the public domain. The analyses focused on the portion of the genome transcribed into non-coding transcripts, which historically have been poorly studied and received less focus. This revealed that Mtb infection in HIV prominently up-regulates the expression of long non-coding RNA (lncRNA) genes DAAM2-AS1, COL4A2-AS1, LINC00599, AC008592.1, and CLRN1-AS1 and down-regulates the expression of lncRNAs AC111000.4, AC100803.3, AC016168.2, AC245100.7, and LINC02073. It also revealed that ART down-regulates the expression of some lncRNA genes (COL4A2-AS1, AC079210.1, MFA-AS1, and LINC01993) that are highly up-regulated in HIV-TB patients. Furthermore, the interrogation of the genomic regions that are associated with regulated lncRNAs showed enrichment for biological processes linked to immune pathways in TB-infected conditions. However, intriguingly, TB patients treated with ART showed completely opposite and non-overlapping pathways. Our findings suggest that lncRNAs could be used to identify critical diagnostic, prognostic, and treatment targets for HIV-TB patients. Full article