Search

Abstract The purpose of vehicle reidentification is to distinguish the same vehicle from different vehicles using different cameras. The main challenge of this task is the significant intra‐instance discrepancy of the same vehicle from different views and the subtle inter‐instance differences of similar vehicles from the same views. To address this problem, researchers have attempted to align features from different views, such as using additional metadata (colour, type, key points, mask, etc.) to improve performance. Although these attempts improve the performance of vehicle reidentification, considerable efforts are required to create additional precise annotations to the data before using these methods. This results in expensive data preparation costs, rendering these methods less convenient to use. Therefore, we propose a novel deep learning network, called a mixed‐attention‐based regional soft partition network, to address this problem. This network does not require additional metadata annotations; it only trains the identity label as a supervision signal and uses soft partition attention to identify specific vehicle regions. Experiments showed that the performance of the proposed method was comparable to that of the state‐of‐the‐art method with additional annotations on the VeRri‐776 and VERI‐Wild datasets.

Abstract Aims/Introduction Several epidemiological studies investigated the effect of Helicobacter pylori infection on diabetes, but the conclusions remained inconsistent. We aimed to explore the relationship between H. pylori infection and diabetes, as well as glycemic metabolism profiles. Materials and Methods A cross‐sectional study including 58,482 Chinese adults was carried out between January 2016 and December 2017. H. pylori infection was diagnosed by the 13C‐urea breath test. Multivariate regression analyses were carried out to evaluate the association of H. pylori infection with diabetes. Results Of the 58,482 participants, 3,449 (5.9%) had diabetes. The H. pylori‐positive participants had a higher rate of diabetes (7.3% vs 5.2%, P

Background Cardiovascular health (CVH) status is associated with cardiovascular diseases (CVD). However, evidence for association of CVH change with risk of CVD is scarce. Methods and Results Seven metrics (smoking status, body mass index, physical activity, diet, total cholesterol, blood pressure, and fasting blood glucose) were used to evaluate the CVH status. Having 0 to 2, 3 to 4, and 5 to 7 ideal cardiovascular metrics were categorized as low, moderate, and high CVH status, respectively. Change in CVH status was assessed from 2006/2007 to 2010/2011. We calculated lifetime risk of CVD using a modified Kaplan–Meier method, and life expectancy was evaluated via the multistate lifetable method. There were 82 349 participants included in our analysis. At 35 years index age, the age‐adjusted incident rate and lifetime risk of CVD were increased with decreasing number of ideal CVH metrics. The direction of change in status of CVH was consistently associated with age‐adjusted incident rate and lifetime risk of CVD. At 35 years index age, improvement from low to moderate (37.6% [95% CI, 32.8%–42.4%]) or to high status (24.4% [95% CI, 12.7%–36.0%]) had lower lifetime risk of CVD compared with consistently low status (44.6% [95% CI, 40.8%–48.5%]). The improvement in CVH could prolong the years of life free from CVD. The pattern of incident rate and lifetime risk across change in CVH status was similar at 45 and 55 years index age. Conclusions Higher number of CVH metrics was associated with lower lifetime risk of CVD. The improvement of CVH status could reduce the lifetime risk of CVD and prolonged the year of life free from CVD.