a model to recover topology can enrich the representation power of point clouds. To this end, we propose a new neural network module dubbed Edge-Conv suitable for CNN-based high-level tasks on point clouds including classification and segmentation. EdgeConv acts on graphs dynamically computed in each layer of the network. It is differentiable and can be plugged into existing architectures. Compared to existing modules operating in extrinsic space or treating each point independently, EdgeConv has several appealing properties: It incorporates local neighborhood information; it can be stacked applied to learn global shape properties; and in multi-layer systems affinity in feature space captures semantic characteristics over potentially long distances in the original embedding. We show the performance of our model on standard benchmarks including ModelNet40, ShapeNetPart, and S3DIS.

No abstract

No abstract

We aim to assess the level of family burden of schizophrenia patients and identify its predicting factors in a rural community sample of China. A sample of 327 primary caregivers was recruited through a one-stage cluster sampling in Ningxiang County of Hunan province, China. Family burden was assessed using the Family Burden Interview Schedule (FBIS) of Pai and Kapur. Our results showed that the mean score of FBIS was 23.62±9.76 (range, 0–48), with over half (52%) caregivers reported their family burden being moderate and severe. Among the six domains of family burden, financial burden (76%) was the commonest burden, while disruption of family interactions (37%) was the least mentioned. A multivariate analysis of family burden revealed that patient being admitted for over 3 times, caregiver being female, having a middle school education, and with additional dependents, as well as higher care network function were positive predictors of family burden, while higher patient function and family function, and increasing patient age were negative predictors of family burden.Intervention to decrease family burden may be best served by improving family function and exploring alternative care model instead of hospitalization.