Browsing Research Publications and Outputs by subject "0801 Artificial Intelligence and Image Processing"
-
Adversarial Recurrent Time Series Imputation
Published 2020For the real-world time series analysis, data missing is a ubiquitously existing problem due to anomalies during data collecting and storage. If not treated properly, this problem will seriously hinder the classification, ...Article -
Dual-Path Adversarial Learning for Fully Convolutional Network (FCN)-Based Medical Image Segmentation
Published 2018-01-01Segmentation of regions of interest (ROIs) in medical images is an important step for image analysis in computer-aided diagnosis systems. In recent years, segmentation methods based on fully convolutional networks (FCNs) ...Article -
Iterative Privileged Learning
Published 2020While in the learning using privileged information paradigm, privileged information may not be as informative as example features in the context of making accurate label predictions, it may be able to provide some effective ...Article -
Long-Term Video Prediction via Criticization and Retrospection
Published 2020Video prediction refers to predicting and generating future video frames given a set of consecutive frames. Conventional video prediction methods usually criticize the discrepancy between the ground-truth and predictions ...Article -
Multi-Label Classification of Multi-Modality Skin Lesion via Hyper-Connected Convolutional Neural Network
Published 2020-01-01Objective: Clinical and dermoscopy images (multi-modality image pairs) are routinely used sequentially in the assessment of skin lesions. Clinical images characterize a lesion’s geometry and color; dermoscopy depicts ...Article -
Multi-task Learning for Blind Source Separation
Published 2018Blind source separation (BSS) aims to discover the underlying source signals from a set of linear mixture signals without any prior information of the mixing system, which is a fundamental problem in signal and image ...Article -
Packing Convolutional Neural Networks in the Frequency Domain
Published 2019Deep convolutional neural networks (CNNs) are successfully used in a number of applications. However, their storage and computational requirements have largely prevented their widespread use on mobile devices. Here we ...Article -
Recurrent Feature Fusion Learning for Multi-Modality PET-CT Tumor Segmentation
Published 2021Background and Objective: [18F]-Fluorodeoxyglucose (FDG) positron emission tomography – computed tomography (PET-CT) is now the preferred imaging modality for staging many cancers. PET images characterize tumoral glucose ...Article -
Review of Robot Skin: A Potential Enabler for Safe Collaboration, Immersive Teleoperation, and Affective Interaction of Future Collaborative Robots
Published 2021The emerging applications of collaborative robots (cobots) are spilling out from product manufactories to service industries for human care, such as patient care for combating the coronavirus disease 2019 (COVID-19) pandemic ...Article -
Robust learning with imperfect privileged information
Published 2020In the learning using privileged information (LUPI) paradigm, example data cannot always be clean, while the gathered privileged information can be imperfect in practice. Here, imperfect privileged information can refer ...Article -
ROMIR: Robust Multi-view Image Re-ranking
Published 2019Recently, multi-view features have significantly pro- moted the performance of image re-ranking by providing complementary image descriptions. Without loss of generality, in multi-view re-ranking, multiple heterogeneous ...Article -
Self-supervised Pose Adaptation for Cross-Domain Image Animation
Published 2020Image animation is to animate a still image of the object of interest using poses extracted from another video sequence. Through training on a large-scale video dataset, most existing approaches aim to explore disentangled ...Article -
Short-Term Lesion Change Detection for Melanoma Screening With Novel Siamese Neural Network
Published 2021Short-term monitoring of lesion changes has been a widely accepted clinical guideline for melanoma screening. When there is a significant change of a melanocytic lesion at three months, the lesion will be excised to exclude ...Article -
Topology-guided deformable registration with local importance preservation for biomedical images
Published 2018The demons registration (DR) model is well recognized for its deformation capability. However, it might lead to misregistration due to erroneous diffusion direction when there are no overlaps between corresponding regions. ...Article -
Unsupervised Brain Tumor Segmentation using a Symmetric-driven Adversarial Network
Published 2021The aim of this study was to computationally model, in an unsupervised manner, a manifold of symmetry variations in normal brains, such that the learned manifold can be used to segment brain tumors from magnetic resonance ...Article