A5006412187- Domain Adaptation and Few-Shot Learning
- Remote-Sensing Image Classification
- Neurological disorders and treatments
- Combustion and Detonation Processes
- Functional Brain Connectivity Studies
- Combustion and flame dynamics
- Botulinum Toxin and Related Neurological Disorders
- Advanced Combustion Engine Technologies
- Parkinson's Disease Mechanisms and Treatments
- Multimodal Machine Learning Applications
- Human Pose and Action Recognition
- Machine Learning and Data Classification
- Network Security and Intrusion Detection
- Underwater Vehicles and Communication Systems
- RNA modifications and cancer
- Hand Gesture Recognition Systems
- Protein Degradation and Inhibitors
- Advanced Image and Video Retrieval Techniques
- Viral Infections and Outbreaks Research
- RNA and protein synthesis mechanisms
- Stroke Rehabilitation and Recovery
- Algorithms and Data Compression
- Multiple Sclerosis Research Studies
- Robotics and Automated Systems
- CAR-T cell therapy research
First Affiliated Hospital Zhejiang University
2024
Harbin University of Science and Technology
2024
University of British Columbia
2017-2023
Zhejiang University
2017-2023
Institute of Acoustics
2014-2017
Chinese Academy of Sciences
2014-2017
Objective To investigate the molecular function of splicing factor SRSF6 in colorectal cancer (CRC) progression and discover candidate chemicals for therapy through targeting SRSF6. Design We performed comprehensive analysis expression 311 CRC samples, The Cancer Genome Atlas Gene Expression Omnibus (GEO) database. Functional was vitro vivo . SRSF6-regulated alternative (AS) its binding motif were identified by next-generation RNA-sequencing RNA immunoprecipitation sequencing (RIP-seq),...
The utilization of Artificial Intelligence (AI) for assessing motor performance in Parkinson's Disease (PD) offers substantial potential, particularly if the results can be integrated into clinical decision-making processes. However, precise quantification PD symptoms remains a persistent challenge. current standard Unified Rating Scale (UPDRS) and its variations serve as primary tools evaluating PD, but are time-intensive prone to inter-rater variability. Recent work has applied data-driven...
Annotated images are required for supervised model training and evaluation in aerial image classification. Manually annotating is arduous expensive, especially images, which often cover a large land area with multiple labels. A recent trend conducting such annotation tasks through crowdsourcing, where annotated by volunteers or paid workers (e.g., Open Street Map) online from scratch. However, crowdsourcing annotations, the quality cannot be guaranteed, incompleteness incorrectness two major...
Recent domain adaptation work tends to obtain a uniformed representation in an adversarial manner through joint learning of the discriminator and feature generator. However, this approach could render sub-optimal performances due two potential reasons: First, it might fail consider task at hand when matching distributions between domains. Second, generally treats source target data same way. In our opinion, which serves adaption purpose should be supplementary, whereas mainly needs...
In this article, we aim to learn a unified representation of images from satellite/aerial/ground views by exploring their underlying correlations. Inspired recent advances in domain adaptation (DA), propose novel task-specific DA method for purpose. Different traditional methods, proposed not only applies classifiers <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> but also introduces domain-specific tasks different domains during the...
Most publicly available datasets for image classification are with single labels, while images inherently multi-labeled in our daily life. Such an annotation gap makes many pre-trained single-label models fail practical scenarios. This issue is more concerned aerial images: Aerial data collected from sensors naturally cover a relatively large land area multiple annotated datasets, which (e.g., UCM, AID), single-labeled. As manually annotating multi-label would be time/labor-consuming, we...
This paper tackles a novel and challenging problem—3D hand pose estimation (HPE) from single RGB image using partial annotation. Most HPE methods ignore the fact that keypoints could be partially visible (e.g., under occlusions). In contrast, we propose deep-learning framework, PA-Tran, jointly estimates status 3D with two dependent branches. The regression branch consists of Transformer encoder which is trained to predict set target keypoints, given an input status, position, visual...
Abstract Aims In cancer biology, the aberrant overexpression of eukaryotic translation initiation factor 5A2 (EIF5A2) has been correlative with an ominous prognosis, thereby underscoring its pivotal role in fostering metastatic progression. Consequently, EIF5A2 garnered significant attention as a compelling prognostic biomarker for various malignancies. Our research endeavors were thus aimed at elucidating utility and significance robust indicator outcome prediction. Method An exhaustive...
The human brainstem is an anatomically complex and compact structure, many neurologic diseases are frequently associated with dysfunction. Despite its importance in brain functioning neurodegenerative processes, the functional sub-structures relatively unexplored medical image analysis. Here we present a data-driven framework to extract sub-regions from brainstem. We first apply novel motion correction scheme A simple network then derived by examining correlation of BOLD signals between...
In this paper, we present an architecture that allows the underwater acoustic target simulator to update firmware and be controlled through a wireless method. It is useful desirable way for research activities allowing researchers quickly efficiently perform experiments on active sonar system would otherwise costly time-consuming. This designed embedded operating DSP/BIOS, realized evaluated self-made TMS320C6455 DSP platform. The scientific experiment aboard anti-frogman project has proved...