This paper presents a comprehensive study of deep correlation features on image style classification. Inspired by that, correlation between feature maps can effectively describe image texture, and we ...design various correlations and transform them into style vectors, and investigate classification performance brought by different variants. In addition to intralayer correlation, interlayer correlation is proposed as well, and its effectiveness is verified. After showing the effectiveness of deep correlation features, we further propose a learning framework to automatically learn correlations between feature maps. Through extensive experiments on image style classification and artist classification, we demonstrate that the proposed learnt deep correlation features outperform several variants of convolutional neural network features by a large margin, and achieve the state-of-the-art performance.
With the idea of social network analysis, we propose a novel way to analyze movie videos from the perspective of social relationships rather than audiovisual features. To appropriately describe ...role's relationships in movies, we devise a method to quantify relations and construct role's social networks, called RoleNet. Based on RoleNet, we are able to perform semantic analysis that goes beyond conventional feature-based approaches. In this work, social relations between roles are used to be the context information of video scenes, and leading roles and the corresponding communities can be automatically determined. The results of community identification provide new alternatives in media management and browsing. Moreover, by describing video scenes with role's context, social-relation-based story segmentation method is developed to pave a new way for this widely-studied topic. Experimental results show the effectiveness of leading role determination and community identification. We also demonstrate that the social-based story segmentation approach works much better than the conventional tempo-based method. Finally, we give extensive discussions and state that the proposed ideas provide insights into context-based video analysis.
Few-shot open-set recognition (FSOR) is the task of recognizing samples in known classes with a limited number of annotated instances while also detecting samples that do not belong to any known ...class. This is a challenging problem because the models must learn to generalize from a small number of labeled samples and distinguish them from an unlimited number of potential negative examples. In this paper, we propose a novel approach called overall positive prototype to effectively improve performance. Conceptually, negative samples would distribute throughout the feature space and are hard to be described. From the opposite viewpoint, we propose to construct an overall positive prototype that acts as a cohesive representation for positive samples that distribute in a relatively smaller neighborhood. By measuring the distance between a query sample and the overall positive prototype, we can effectively classify it as either positive or negative. We show that this simple yet innovative approach provides the state-of-the-art FSOR performance in terms of accuracy and AUROC.
Display omitted
•We propose the concept of overall positive prototype (OPP) to summarize positive prototypes.•The OPP is employed to solve the few-shot open-set image recognition problem.•Comprehensive evaluation and ablation studies show OPP achieves the state-of-the-art performance.
In this paper, I argue that rigorous attempts to grasp the challenges unique to transdisciplinary projects in the Global South (TPGSs) require an understanding of the target state's ...political-economic dynamics, which can undermine TPGSs. In this regard, I harness social-conflict theory to examine how and why Cambodia's political-economic dynamics affected my own transdisciplinary project, which addressed dam-induced problems in the northeast of the country from 2018 to 2021. The present paper's findings clarify the relationships among various nonacademic TPGS stakeholders-a topic that has attracted little attention from transdisciplinarians but that can significantly shape TPGS outcomes.
Objective
The study's objective was to investigate the association of fat mass index (FMI) and fat‐free mass index (FFMI) with all‐cause mortality and cause‐specific mortality in the Chinese ...population.
Methods
A total of 422,430 participants (48.1% men and 51.9% women) from the Taiwan MJ Cohort with an average follow‐up of 9 years were included.
Results
The lowest (Q1) and highest (Q5) quintiles of FMI and FFMI were associated with increased all‐cause mortality. Compared with those in the third quintile (Q3) group of FMI, participants in Q1 and Q5 groups of FMI had hazard ratios and 95% CI of 1.32 (1.24–1.40) and 1.13 (1.06–1.20), respectively. Similarly, compared with those in Q3 group of FFMI, people in Q1 and Q5 groups of FFMI had hazard ratios of 1.14 (1.06–1.23) and 1.16 (1.10–1.23), respectively. In the restricted cubic spline models, both FMI and FFMI showed a J‐shaped association with all‐cause mortality. People in Q5 group of FFMI had a hazard ratio of 0.72 (0.58–0.89) for respiratory disease.
Conclusions
The mortality risk increases in those with excessively high or low FMI and FFMI, yet the associations between FMI, FFMI, and the risk of death varied across subgroups and causes of death.
Analyzing volleyball videos based on 3D ball trajectories was relatively overlooked before. In this brief, we focus on how ball trajectories can benefit volleyball video analysis. Based on videos ...captured by two cameras from different viewpoints, we detect the volleyball and construct 3D ball trajectories. We then propose a trajectory segmentation and classification method based on BERT (Bidirectional Encoder Representation for Transformer). The volleyball at each frame can be categorized into one of six trajectory classes, e.g., serve and attack, and a long ball trajectory showing the ball being hit back and forth is appropriately segmented. We believe that this is a very first study adopting the language model technique to analyze ball trajectories, and results of trajectory segmentation and classification can enable more advanced volleyball analysis.
This study investigates age-specific prostate-specific antigen (PSA) distributions in Taiwanese men and recommends reference ranges for this population after comparison with other studies. From ...January 1999 to December 2016, a total of 213,986 Taiwanese men aged above 19 years old without history of prostate cancer, urinary tract infection, or prostate infection were recruited from the Taiwan MJ cohort, an ongoing prospective cohort of health examinations conducted by the MJ Health Screening Center in Taiwan. Participants were divided into seven age groups. Simple descriptive statistical analyses were carried out and quartiles and 95th percentiles were calculated for each group as reference ranges for serum PSA in screening for prostate cancer in Taiwanese men. Serum PSA concentration correlated with age (r = 0.274, p<0.001). The median serum PSA concentration (5th to 95th percentile) ranged from 0.7 ng/ml (0.3 to 1.8) for men 20-29 years old (n = 6,382) to 1.6 ng/ml (0.4 to 8.4) for men over 79 years old (n = 504). The age-specific PSA reference ranges are as follows: 20-29 years, 1.80 ng/ml; 30-39 years, 1.80 ng/ml; 40-49 years, 2.0 ng/ml; 50-59 years, 3.20 ng/ml; 60-69 years, 5.60 ng/ml; 70-79 years, 7.40 ng/ml; over 80 years, 8.40 ng/ml. Almost no change occurred in the median serum PSA value in men 50 years old or younger, while a gradual increase was observed in men over 50. Taiwanese men aged 60 years above showed higher 95th percentile serum PSA values compared to Caucasian men and men in other Asian countries but were closer to those of Asian American and African American men. Results indicate significantly different PSA levels correlating to different ethnicities, suggesting that Oesterling's age-specific PSA reference ranges might not be appropriate for Taiwanese men. Our results should be further studied to validate the age-specific PSA reference ranges for Taiwanese men presented in this study.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Scaphoid fractures are the most common carpal fractures. Diagnosing scaphoid fractures is challenging. Recently, cone-beam computed tomography (CBCT) has been shown to be a promising strategy for ...diagnosing scaphoid fractures. The diagnostic performance of CBCT remains inconclusive in the literature. Through a systematic review and meta-analysis, our study aims to determine the diagnostic performance of CBCT for diagnosing scaphoid fractures. Five databases were searched up to March 25, 2020. We included prospective and retrospective studies describing the diagnostic accuracy of CBCT for scaphoid fractures in adult patients. QUADAS-2 tool was used to assess the quality of the included studies. Four studies (n = 350) were included in the meta-analysis. Three of the four studies had high bias risk. The result showed that CBCT had a pooled sensitivity of 0.88 and a pooled specificity of 0.99 for scaphoid fracture diagnosis. The heterogeneities of sensitivity and specificity were substantial. The area under the summary receiver operating characteristic curve was 0.98. No significant publication bias was observed. The result suggested that the diagnostic performance of CBCT for scaphoid fracture was excellent. The certainty of current evidence is low. Further well-designed studies with large sample sizes are warranted to confirm this finding.
Residual networks (ResNets) have been utilized for various computer vision and image processing applications. The residual connection improves the training of the network with better gradient flow. A ...residual block consists of a few convolutional layers having trainable parameters, which leads to overfitting. Moreover, the present residual networks are not able to utilize the high- and low-frequency information suitably, which also challenges the generalization capability of the network. In this paper, a frequency-disentangled residual network (FDResNet) is proposed to tackle these issues. Specifically, FDResNet includes separate connections in the residual block for low- and high-frequency components, respectively. Basically, the proposed model disentangles the low- and high-frequency components to increase the generalization ability. Moreover, the computation of low- and high-frequency components using fixed filters further avoids the overfitting. The proposed model is tested on benchmark CIFAR-10/100, Caltech, and TinyImageNet datasets for image classification. The performance of the proposed model is also tested in the image retrieval framework. It is noticed that the proposed model outperforms its counterpart residual model. The effect of kernel size and standard deviation is also evaluated. The impact of the frequency disentangling is also analyzed using a saliency map.