- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Advanced Neural Network Applications
- AI in cancer detection
- Medical Image Segmentation Techniques
- Multimodal Machine Learning Applications
- Neurological Disease Mechanisms and Treatments
- Visual Attention and Saliency Detection
- Intracerebral and Subarachnoid Hemorrhage Research
- Body Composition Measurement Techniques
- Acute Ischemic Stroke Management
- Hand Gesture Recognition Systems
- Cutaneous Melanoma Detection and Management
- Nuclear Receptors and Signaling
- Airway Management and Intubation Techniques
- Nutrition and Health in Aging
- Infrared Thermography in Medicine
- Educational Technology and Pedagogy
- Pregnancy and preeclampsia studies
- Adrenal and Paraganglionic Tumors
- COVID-19 diagnosis using AI
- Genomics, phytochemicals, and oxidative stress
- Neurosurgical Procedures and Complications
- Medicinal Plants and Neuroprotection
- Diverse Approaches in Healthcare and Education Studies
China National Institute of Standardization
2021-2023
Aerospace Center Hospital
2023
Peking University
2023
East China Normal University
2022
Ping An (China)
2021
Tangshan Gongren Hospital
2016-2020
Fudan University
2014-2018
We present a Temporal Context Network (TCN) for precise temporal localization of human activities. Similar to the Faster-RCNN architecture, proposals are placed at equal intervals in video which span multiple scales. propose novel representation ranking these proposals. Since pooling features only inside segment is not sufficient predict activity boundaries, we construct explicitly captures context around proposal it. For each proposal, uniformly sampled pair scales and input convolutional...
Liraglutide is a type of glucagon‑like‑peptide 1 receptor agonist, which has been reported as novel antidiabetic agent with numerous benefits, including cardiovascular and neuroprotective effects. To the best our knowledge, few studies to date have potential mechanism underlying effects liraglutide on rats 2 diabetes mellitus (T2DM). The present study aimed investigate actions in diabetic determine mechanisms these A total 30 male T2DM Goto‑Kakizaki (GK) (age, 32 weeks; weight, 300‑350 g) 10...
We propose a multistream multitask deep network for joint human detection and head pose estimation in RGB-D videos. To achieve high accuracy, we jointly utilize appearance, shape, motion information as inputs. Based on the depth information, generate scale invariant proposals, which are then fed into novel contextual region of interest pooling (CRP) layer our network. This CRP has two branches to deal with each subject. The proposed method outperforms state-of-the-art approaches three public...
We present a Temporal Context Network (TCN) for precise temporal localization of human activities. Similar to the Faster-RCNN architecture, proposals are placed at equal intervals in video which span multiple scales. propose novel representation ranking these proposals. Since pooling features only inside segment is not sufficient predict activity boundaries, we construct explicitly captures context around proposal it. For each proposal, uniformly sampled pair scales and input convolutional...
Background/Aims: To explore the effects of sulforaphane (SFN) on neuronal apoptosis in hippocampus and memory impairment diabetic rats. Methods: Thirty male rats were randomly divided into normal control, model SFN treatment groups (N = 10 each group). Streptozotocin (STZ) was applied to establish model. Water Morris maze task test learning memory. Tunel assaying used detect hippocampus. The expressions Caspase-3 myeloid cell leukemia 1(MCL-1) detected by western blotting. Neurotrophic...
Human detection has received great attention during the past few decades, which is yet still a challenging problem. In this paper, we focus on problem of 3-D human detection, i.e., finding bodies and determining their coordinates in complex space using depth data only. Since traditional sliding-window-based approaches for target localization are time-consuming recent deep-learning-based object detectors generate too many region proposals, propose to utilize candidate head-top locating stage...
BACKGROUND:In the recent years, there has been increasing interest in traditional Chinese medicine as a neuroprotective nutrient management of chronic neurodegenerative disease, such diabetic cognitive decline. Astragalus polysacharin (APS), herb extract, is biologically active treatment for diseases. Therefore, present study, we investigated effects APS (20 mg/kg) on diabetes-induced memory impairments Sprague-Dawley (SD) rats and explored its underlying mechanisms action. MATERIAL AND...
Although previous studies have proposed predictive models of gestational diabetes mellitus (GDM) based on maternal status, they do not always provide reliable results. The present study aimed to create a novel model that included ultrasound data fat distribution and serum inflammatory factors. clinical 1,158 pregnant women treated at Tangshan Gongren Hospital eight other flagship hospitals in Tangshan, including the First group, Ninth group rehabilitation hospital, railway central Fengnan...
Real-time human detection is important for a wide range of applications. In this paper, two-staged method has been developed real-time in cluttered and dynamic environments with depth data. We start generating set possible head-tops to ensure all locations are included. To end, novel physical radius-depth (PRD) detector proposed quickly detect candidates. The second stage applies convolutional neural network (CNN), aiming at extracting feature upper body automatically instead hand-crafting,...
With the development of depth cameras such as Kinect and Intel Realsense, RGB-D based human detection receives continuous research attention due to its usage in a variety applications. In this paper, we propose new Multi-Glimpse LSTM (MG-LSTM) network, which multi-scale contextual information is sequentially integrated promote performance. Furthermore, feature fusion strategy on our MG-LSTM network better incorporate RGB information. To best knowledge, first attempt utilize structure for...
This paper proposes a two-staged approach to real-time human detection in cluttered environments using RGB-D camera. The first stage is novel physical blob (P-Blob) that can quickly find plausible heads. second uses combination of upper-body features filter out false positives. Experiment results on three publicly available datasets show the proposed method reliably detect people video real time.
Recognition of glomeruli lesions is the key for diagnosis and treatment planning in kidney pathology; however, coexisting glomerular structures such as mesangial regions exacerbate difficulties this task. In paper, we introduce a scheme to recognize fine-grained from whole slide images. First, focal instance structural similarity loss proposed drive model locate all types precisely. Then an Uncertainty Aided Apportionment Network designed carry out visual classification without bounding-box...
Tissue segmentation is the mainstay of pathological examination, whereas manual delineation unduly burdensome. To assist this time-consuming and subjective step, researchers have devised methods to automatically segment structures in images. Recently, automated machine deep learning based dominate tissue research studies. However, most approaches are supervised developed using a large number training samples, which pixel-wise annotations expensive sometimes can be impossible obtain. This...
Real-time human detection in crowded and dynamic environments poses a significant challenge, due to complex background, occlusion different poses. In this paper, we propose two-staged approach using color depth data taken by an RGB-D camera. The first stage is find plausible head-top locations quickly image. second extract effective discrimination features from discard the false positives with support vector machine. experiments on publicly available office dataset, mobile platform dataset...
Efficient and robust detection of humans has received great attention during the past few decades. This paper presents a two-staged approach for human in RGB-D images. As traditional sliding window-based methods target localization are often time-consuming, we propose to use super-pixel method depth data efficiently locate plausible head-top locations first stage. In second stage, Random Ferns seek features by combining information from different image spaces, which can select most...
Double-lumen tube (DLT) intubation in lateral decubitus position is rarely reported. We designed this study to evaluate the feasibility of VivaSight double-lumen (VDLT) assisted by video laryngoscope patients. Patients undergoing elective video-assisted thoracoscopic surgery (VATS) for lung lobectomy were assessed eligibility between January 2022 and December, 2022. Eligible patients randomly allocated into supine group (group S) L) a computer-generated table random numbers. The prime...
Introduction: Paragangliomas (PGs) or extra-adrenal pheochromocytomas are rare neuroendocrine neoplasms of ubiquitous distribution. Those that produce excess catecholamine categorized as functional, and those do not nonfunctional. Although modern medical technology is becoming more widespread, there still substantial risks misdiagnosis missed diagnosis PGs. Case presentation: A 38-year-old woman who lived in an autonomous region inner Mongolia presented complaining having experienced...