A generative model is presented for two types of person image generation in this paper. First, this model is applied to pose-guided person image generation, i.e., converting the pose of a source person image to the target pose while preserving the texture of that source person image. Second, this model is also used for clothing-guided person image generation, i.e., changing the clothing texture of a source person image to the desired clothing texture. The core idea of the proposed model is to establish the multi-scale correspondence, which can effectively address the misalignment introduced by transferring pose, thereby preserving richer information on appearance. Specifically, the proposed model consists of two stages: 1) It first generates the target semantic map imposed on the target pose to provide more accurate guidance during the generation process. 2) After obtaining the multi-scale feature map by the encoder, the multi-scale correspondence is established, which is useful for a fine-grained generation. Experimental results show the proposed method is superior to stateof-the-art methods in pose-guided person image generation and show its effectiveness in clothing-guided person image generation.

No abstract

No abstract

Background. Intracranial infection is a serious complication after neurosurgery. According to a survey, the incidence of intracranial infection is about 2.2%-2.6%, and patients with severe symptoms may even pose a threat to their life safety. Objective. To explore the risk factors for intracranial infection caused by Acinetobacter baumannii after surgery and the clinical effect of sequential therapy of cefoperazone/sulbactam sodium. Methods. In this study, a retrospective study was used. In this case-control study, 48 cases of intracranial Acinetobacter baumannii infection after neurosurgery in our hospital from January 2016 to December 2021 were selected as the infection group, and 96 patients without intracranial infection after surgery during the same period were selected as the control group to study all kinds of related factors and analyze the risk factors for intracranial Acinetobacter baumannii infection; in addition, in accordance with the therapeutic regimen for anti-infection, the infection group was divided into the tigecycline group (patients with tigecycline therapy in this group) and the combined group (patients with tigecycline combined with cefoperazone/sulbactam sequential therapy), with 24 cases in each group in order to compare the therapeutic effects of the two groups. Results. Logistic regression factor model results show that increasing age of patients, surgical treatment for intracranial tumor or craniocerebral trauma, postoperative drainage time (≥3 days), and postoperative hospital stay (≥10 days) were the risk factors for postoperative intracranial infection of Acinetobacter baumannii in neurosurgical patients ( P < 0.05 ), and postoperative prophylactic antibiotic treatment can reduce the incidence of intracranial infection ( P < 0.05 ). The cerebrospinal fluid nucleated cell count, serum CRP, and serum PCT in the combined group 72 h after treatment were lower than those in the tigecycline group, and the difference was statistically significant ( P < 0.05 ). Compared with the clinical efficacy after 72-hour treatment, the cure rate and effective rate in the combined treatment group were 83.33% and 16.67%, respectively, and those in the tigecycline group were 54.17% and 33.33%, respectively. The invalid interest rate was 12.50%, and the combined treatment group was superior to the tigecycline group ( P < 0.05 ). Conclusion. For patients with craniocerebral surgery, targeted preventive interventions should be carried out for the risk factors that may lead to intracranial Acinetobacter baumannii infection. The clinical effect of tigecycline combined with cefoperazone and sulbactam sodium sequentially in the treatment of intracranial Acinetobacter baumannii infection is better.

No abstract