A5101442384- Advanced Neural Network Applications
- Robotics and Sensor-Based Localization
- Maternal Mental Health During Pregnancy and Postpartum
- Advanced Vision and Imaging
- Birth, Development, and Health
- Pregnancy and preeclampsia studies
- Lower Extremity Biomechanics and Pathologies
- Osteoarthritis Treatment and Mechanisms
- Video Surveillance and Tracking Methods
- Pregnancy and Medication Impact
- Fetal and Pediatric Neurological Disorders
- Domain Adaptation and Few-Shot Learning
- Industrial Vision Systems and Defect Detection
- Neuroendocrine regulation and behavior
- Advanced Data Storage Technologies
- Child and Adolescent Psychosocial and Emotional Development
- Augmented Reality Applications
- Musculoskeletal pain and rehabilitation
- Diabetic Foot Ulcer Assessment and Management
- Error Correcting Code Techniques
- Caching and Content Delivery
- Cleft Lip and Palate Research
- Thyroid Disorders and Treatments
- Human Pose and Action Recognition
- Neuroscience of respiration and sleep
The University of Melbourne
2024-2025
North China University of Technology
2024
Anhui Medical University
2020-2023
Ministry of Education of the People's Republic of China
2022-2023
Liaoning University
2023
Qinghai Normal University
2021-2023
Nanjing Normal University
2023
Shenyang Institute of Automation
2020-2022
Chinese Academy of Sciences
2020-2022
University of Chinese Academy of Sciences
2020-2022
In this work, we propose a novel one-stage and keypoint-based framework for monocular 3D object detection using only RGB images, called KM3D-Net. 2D requires deep neural network to predict properties of objects, as it is semanticity-aware task. For image-based detection, argue that the combination geometric constraints are needed synergistically estimate appearance-related spatial-related information. Here, design fully convolutional model keypoints, dimension, orientation, combine these...
While separately leveraging monocular 3D object detection and 2D multi-object tracking can be straightforwardly applied to sequence images in a frame-by-frame fashion, stand-alone tracker cuts off the transmission of uncertainty from detector while cannot pass error differentials back detector. In this work, we propose jointly training only videos an end-to-end manner. The key component is novel spatial-temporal information flow module that aggregates geometric appearance features predict...
In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. Most successful detectors take the projection constraint from bounding box to 2D as important component. Four edges of a provide only four constraints performance deteriorates dramatically with small error detector. Different these approaches, our method predicts nine perspective keypoints image space, then utilize geometric relationship perspectives recover dimension, location, orientation...
Objectives To determine if physiotherapists can deliver a clinically effective very low energy diet (VLED) supplementary to exercise in people with knee osteoarthritis (OA) and overweight or obesity. Methods 88 participants OA body mass index (BMI) >27 kg/m 2 were randomised either intervention (n=42: VLED including two daily meal replacement products control) control (n=46: exercise). Both interventions delivered by unblinded via six videoconference sessions over 6 months. The primary...
Introduction Patellofemoral pain affects one-third of adolescents, with most experiencing symptoms into adulthood. Guidelines recommend exercise and foot orthoses based on clinical trials in adults; however, these approaches have been found to be ineffective poor adherence adolescents. ‘Minimalist’ shoes can reduce patellofemoral joint forces may therefore a promising low burden management approach for pain. This article outlines the protocol randomised trial (RCT) that aims determine if...
Although the recent image-based 3D object detection methods using Pseudo-LiDAR representation have shown great capabilities, a notable gap in efficiency and accuracy still exist compared with LiDAR-based methods. Besides, over-reliance on stand-alone depth estimator, requiring large number of pixel-wise annotations training stage more computation inferencing stage, limits scaling application real world. In this paper, we propose an efficient accurate method from stereo images, named RTS3D....
Abstract Context Maternal thyroid hormone trajectories are a better predictor of offspring’s neurodevelopment than levels in single trimester pregnancy. Programming effect uterine hormonal environment on health is usually sex-specific. Objective To examine the sex-specific preschoolers’ behavioral development. Design Based Ma’ anshan Birth Cohort China, pregnant women were recruited at their first antenatal checkup from May 2013 to September 2014. Setting and Child Health Hospital China....
In this work, we propose a novel single-shot and keypoints-based framework for monocular 3D objects detection using only RGB images, called KM3D-Net. We design fully convolutional model to predict object keypoints, dimension, orientation, then combine these estimations with perspective geometry constraints compute position attribute. Further, reformulate the geometric as differentiable version embed it into network reduce running time while maintaining consistency of outputs in an end-to-end...
The after-school program is a crucial initiative for implementing the Double Reduction policy; however, prior research has not provided conclusive evidence on whether extended school hours contribute to students’ cognitive and non-cognitive development or which types of services are more beneficial student development. This study analyzed 37 programs from 18 publications using meta-analytic techniques, results indicated that participation in had positive effects despite small effect size (d...
Background: Epidemiological and experimental studies suggest that thyroid peroxidase antibody (TPOAb)- thyroglobulin (TGAb)-positive exposure during gestation may contribute to offspring's adverse neural development. However, limited knowledge is available on the association between joint TPOAb TGAb children's emotional behavioral Furthermore, sex-specific effect developmental process of preschoolers' emotions behaviors unknown. The present research intends examine TPOAb- TGAb-positive in...