Search

Fashion style is expressed through the way clothing and accessories are put together, as well as the silhouettes, textiles, colors, and shape details of each fashion item. The challenge of style classification lies in the wide visual variation within the same style and the existence of visually similar styles. Fashion experts categorize fashion styles not only by global appearance but also by the attributes of individual items and their combinations. We propose an item-region-based fashion style classification network (IRSN) that effectively classifies fashion styles by analyzing item-level features and their combinations. IRSN extracts item features using item region pooling (IRP), analyzes them separately, and aggregates them using gated feature fusion (GFF). In addition, IRSN applies a dual-backbone architecture that combines a domain-specific feature extractor and a general feature extractor pretrained with a large general image-text dataset. In the experiment, we evaluated IRSN variants based on six widely used backbones, including EfficientNet, ConvNeXt, and SwinTransformer. The IRSN models outperformed their baseline models by an average of 8.9% and a maximum of 16.7% on the FashionStyle14 dataset, and by an average of 9.4% and a maximum of 17.0% on the ShowniqV3 dataset. The visualization results support that the IRSN models are more effective than the baseline models in capturing differences between similar style classes. [ABSTRACT FROM AUTHOR]

We propose a large-scale Hangul font recognizer that is capable of recognizing 3300 Hangul fonts. Large-scale Hangul font recognition is a challenging task. Typically, Hangul fonts are distinguished by small differences in detailed shapes, which are often ignored by the recognizer. There are additional issues in practical applications, such as the existence of almost indistinguishable fonts and the release of new fonts after the training of the recognizer. Only a few recently developed font recognizers are scalable enough to recognize thousands of fonts, most of which focus on the fonts for western languages. The proposed recognizer, HanFont, is composed of a convolutional neural network (CNN) model designed to effectively distinguish the detailed shapes. HanFont also contains a font clustering algorithm to address the issues caused by indistinguishable fonts and untrained new fonts. In the experiments, HanFont exhibits a recognition rate of 94.11% for 3300 Hangul fonts including numerous similar fonts, which is 2.49% higher than that of ResNet. The cluster-level recognition accuracy of HanFont was 99.47% when the 3300 fonts were grouped into 1000 clusters. In a test on 100 new fonts without retraining the CNN model, HanFont exhibited 57.87% accuracy. The average accuracy for the top 56 untrained fonts was 75.76%. [ABSTRACT FROM AUTHOR]

As the age of Internet of Things (IoT) has come, national-level cyber security measures should be prepared and concrete implementation plans should be established, so that critical infrastructure can be operated and maintained safely, protected from cyber attacks. In addition, IoT services for such infrastructure should be capable of closely obtaining and processing information in environments experienced by users. To provide reliable IoT services for critical infrastructure utilizing IoT devices, based on an understanding of the vulnerabilities of IoT technology and cutting-edge cyber threats, this paper proposes methods for predicting errors that may occur in physical situations, where things are connected to each other and analyzing and modeling the errors as a functional requirement. In addition to technical measures, security guidelines are presented for individual fields, such as policy, organization, manpower, budget, industry, R&D, and education. [ABSTRACT FROM AUTHOR]

5-FU is an anticancer drug that is widely used to treat cancers, including colorectal cancer (CRC); however, chemoresistance to 5-FU remains an important problem to be resolved. The role of microRNAs (miRs) in chemosensitivity has recently been studied in the development of therapeutic strategies to overcome drug resistance. Here, we focused on miR-96, which has been reported to demonstrate chemosensitivity. We investigated whether 5-FU sensitivity may be modulated by miR-96 in monolayer cells and whether this relationship also applies for drug resistance in 3D tumor spheroids (TSs). When the level of miR-96 increased, the expression of the anti-apoptotic regulator XIAP and p53 stability regulator UBE2N decreased, resulting in increased apoptosis and growth inhibition following 5-FU exposure. Transfection of miR-96 inhibitors resulted in an overexpression of XIAP and UBE2N, yet only minimal change was induced in apoptosis. Nonetheless, luciferase assay failed to show direct interactions between miR-96 and these genes. In TSs, 5-FU resistance corresponded to a significantly lower level of miR-96, however only XIAP, not UBE2N, was up-regulated demonstrating partial agreement with the 2D condition regarding target expression. Overall, these results suggest that miR-96 may modulate 5-FU sensitivity in CRC cells by promoting apoptosis; however, differential expression of target genes in TSs warrants further studies on the 5-FU resistance mechanism under 3D conditions. [ABSTRACT FROM AUTHOR]

T-cadherin is frequently down regulated in various cancers, however, the underlying mechanisms responsible have yet to be elucidated. A genome wide association study of a cohort of Korean adults revealed that the T-cadherin rs3865188 single nucleotide polymorphism (SNP) was associated with serum Adiponectin levels and that its genotypic variants were correlated with risk for colorectal cancer (CRC). To test the function of rs12444338, a SNP tightly linked to the rs3865188 SNP, in T-cadherin transcriptional regulation in colorectal cancer, its effect on transcriptional activity and the capacity of binding activity attributable to allelic variation of the rs12444338 SNP was investigated. An electrophoretic-mobility-shift assay (EMSA) revealed a specific nucleoprotein complex unique to the T allele probe, which displayed lower promoter activity when compared to the G allele. Based on the results of the EMSA using mutant probes, the consensus sequence of the putative transcription factor binding site was determined. Additionally, candidates for putative binding factors to the T allele were also identified. Collectively, the study data suggested that the rs12444338 SNP was involved in transcriptional regulation of T-cadherin gene (CDH13) and that the differential binding of transcription factors at the rs12444338 SNP resulted in altered gene expression. These results elucidate, at least in part, the regulation of T-cadherin expression in CRC and provide further information regarding the effect of nucleotide variation in its promoter region. [ABSTRACT FROM AUTHOR]