A5037192204- Handwritten Text Recognition Techniques
- Natural Language Processing Techniques
- Autism Spectrum Disorder Research
- Spaceflight effects on biology
- Genetics and Neurodevelopmental Disorders
- Image Processing and 3D Reconstruction
- Industrial Vision Systems and Defect Detection
- Image Retrieval and Classification Techniques
- Domain Adaptation and Few-Shot Learning
- Ergonomics and Musculoskeletal Disorders
- Multimodal Machine Learning Applications
- Topic Modeling
- Family and Disability Support Research
- Web Data Mining and Analysis
- Optical Systems and Laser Technology
- Human-Automation Interaction and Safety
- Face recognition and analysis
- Psychological and Temporal Perspectives Research
- Human Pose and Action Recognition
- Sleep and Work-Related Fatigue
- Multisensory perception and integration
- Neuroscience and Music Perception
- Space Exploration and Technology
- Advanced Image and Video Retrieval Techniques
- Advanced Measurement and Detection Methods
Shanghai Jiao Tong University
2020-2025
University of Science and Technology Beijing
2021-2024
Northwestern Polytechnical University
2024
China Astronaut Research and Training Center
2009-2021
Huazhong Agricultural University
2020
Air Force General Hospital PLA
2019
The incidence of autism spectrum disorders (ASD), a neurodevelopmental condition associated with challenges in social communication, has witnessed remarkable surge recent years, adverse effects on individuals, families, and society at large. Early screening for ensures timely access to interventions, yet lacks systematic methodical approaches objectively quantifying behaviors. In response this, we propose protocol early assistive screening, termed the Express-Needs-with-Pointing (ENP), which...
Sheep body segmentation robot can improve production hygiene, product quality, and cutting accuracy, which is a huge change for traditional manual segmentation. With reference to the New Zealand sheep specification, vision system Cartesian coordinate half-sheep was developed tested. The workflow of designed image acquisition device with an Azure Kinect sensor developed. Furthermore, LabVIEW software processing algorithm then integrated RGBD in order construct automatic system. Based on...
Accurate time perception is clearly essential for the successful implementation of space missions. To elucidate effect microgravity on perception, we used three emotional picture stimuli: neutral, fear, and disgust, in combination with a temporal bisection task to measure 16 male participants' 15 days -6° head-down bed rest, which reliable simulation model most physiological effects spaceflight. We found that: (1) participants showed overestimation fear stimuli middle phase (day 8),...
As key part of aero-engine, blade has the characteristics huge quantity, various shapes, high processing quality requirements and complex processing. It is great significance to develop efficient high-precision non-contact surface size detection for its detection. Optical scanning measurement based on visual tracking becoming an effective reliable method. In order realize system, this paper designs a 3D stereo target, proposes algorithm recognize coded markers target.
The open-set text recognition task is a generalized form of the (close-set) task, where model further challenged to spot and incrementally recognize novel characters in new languages, which also indicate shift language model. In this work, we propose alleviate confounding effect such biases under an setup by learning individual character representations out their context.We Character-First Open-Set Text Recognition framework that treats as first-class citizens cotraining feature extractor...
Autism Spectrum Disorders (ASD) are characterized by impairments in joint attention (JA) comprising two components: responding to JA (RJA) and initiating (IJA). RJA IJA considered interrelated aspects of JA, related different stages infant development. While recent technologies have been used characterize emerging earlier childhood, only a limited number studies attempted explore IJA, which progressively becomes evident as hallmark ASD. This study aims achieve the social recognition both...
Head pose offers vital cues to infer one's social attention in wide applications. Most existing head estimation algorithms have demonstrated competitive results taking high resolution images of frontal view as input. However, these approaches still work poorly if they are fed with low-resolution images. In a more common realistic scene such computer vision assisted autism screening, unconstrained patients that taken from distant cameras often and non-frontal faces. To this end, we present...
Objective To discuss the matters in space cognition study and foresee its development future by reviewing methods, tools results of current study.Literature resource selection Domestic abroad published papers reviews related field. Literature quotation Thirty-one were citied. synthesis There are many stressors, such as microgravity, isolation, confinement, etc. , flight those would influence astronaut's cognition. The has a significant meaning for ensuring success mission crew's safety....
Objective To measure the effects of 72 h-isolation and confinement (IC) with or without sleep deprivation (SD) on attention network functions operation performance manual controlled rendezvous docking task. Methods Twelve healthy male volunteers were randomly divided into 4 groups 3. The experiments done by means self-control cross-over design. Two underwent h IC SD, then recovered for 7 d. After that, they SD. Other 2 identical environments in opposite order. evaluation functional...
<div><br></div><div>Scene text recognition is a popular topic and can benefit various tasks. Although many methods have been proposed for the close-set challenges, they cannot be directly applied to open-set scenarios, where evaluation set contains novel characters not appearing in training set. Conventional require collecting new data retraining model handle these characters, which an expensive tedious process. In this paper, we propose label-to-prototype learning...