Maoying Qiao
YOU?
Author Swipe
View article: EBaR: Efficient Buffer and Resetting for Single-Sample Continual Test-Time Adaptation
EBaR: Efficient Buffer and Resetting for Single-Sample Continual Test-Time Adaptation Open
View article: QuARF: Quality-Adaptive Receptive Fields for Degraded Image Perception
QuARF: Quality-Adaptive Receptive Fields for Degraded Image Perception Open
Advanced Deep Neural Networks (DNNs) perform well for high-quality images, but their performance dramatically decreases for degraded images. Data augmentation is commonly used to alleviate this problem, but using too much perturbed data mi…
View article: QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge
QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge Open
Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a significant challenge in achieving consistent and reliable imag…
View article: Trust-Region Adaptive Frequency for Online Continual Learning
Trust-Region Adaptive Frequency for Online Continual Learning Open
In the paradigm of online continual learning, one neural network is exposed to a sequence of tasks, where the data arrive in an online fashion and previously seen data are not accessible. Such online fashion causes insufficient learning an…
View article: Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processes
Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processes Open
Graph convolutional networks (GCNs) have achieved great success in graph representation learning by extracting high-level features from nodes and their topology. Since GCNs generally follow a message-passing mechanism, each node aggregates…
View article: Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples
Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples Open
Graph Convolutional Neural Networks (GCNs) have been generally accepted to be an effective tool for node representations learning. An interesting way to understand GCNs is to think of them as a message passing mechanism where each node upd…
View article: Early lessons in deploying cameras and artificial intelligence technology for fisheries catch monitoring: where machine learning meets commercial fishing
Early lessons in deploying cameras and artificial intelligence technology for fisheries catch monitoring: where machine learning meets commercial fishing Open
Electronic monitoring (EM) is increasingly used to monitor catch and bycatch in wild capture fisheries. EM video data are still manually reviewed and adds to ongoing management costs. Computer vision, machine learning, and artificial intel…
View article: Deep learning methods applied to electronic monitoring data: automated catch event detection for longline fishing
Deep learning methods applied to electronic monitoring data: automated catch event detection for longline fishing Open
Electronic monitoring (EM) systems have become functional and cost-effective tools for the conservation and sustainable harvesting of marine resources. EM is an alternative to on-board observers, which produces video segments that can subs…
View article: Repulsive Mixture Models of Exponential Family PCA for Clustering
Repulsive Mixture Models of Exponential Family PCA for Clustering Open
The mixture extension of exponential family principal component analysis (EPCA) was designed to encode much more structural information about data distribution than the traditional EPCA does. For example, due to the linearity of EPCA's ess…
View article: Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach
Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach Open
Community is a common characteristic of networks including social networks, biological networks, computer and information networks, to name a few. Community detection is a basic step for exploring and analysing these network data. Typicall…
View article: Diversified Bayesian Nonnegative Matrix Factorization
Diversified Bayesian Nonnegative Matrix Factorization Open
Nonnegative matrix factorization (NMF) has been widely employed in a variety of scenarios due to its capability of inducing semantic part-based representation. However, because of the non-convexity of its objective, the factorization is ge…
View article: Adapting Stochastic Block Models to Power-Law Degree Distributions
Adapting Stochastic Block Models to Power-Law Degree Distributions Open
Stochastic block models (SBMs) have been playing an important role in modeling clusters or community structures of network data. But, it is incapable of handling several complex features ubiquitously exhibited in real-world networks, one o…
View article: Improving Stochastic Block Models by Incorporating Power-Law Degree Characteristic
Improving Stochastic Block Models by Incorporating Power-Law Degree Characteristic Open
Stochastic block models (SBMs) provide a statistical way modeling network data, especially in representing clusters or community structures. However, most block models do not consider complex characteristics of networks such as scale-free …
View article: Diversified probabilistic graphical models
Diversified probabilistic graphical models Open
View article: Diversified Hidden Markov Models for Sequential Labeling
Diversified Hidden Markov Models for Sequential Labeling Open
Labeling of sequential data is a prevalent meta-problem for a wide range of\nreal world applications. While the first-order Hidden Markov Models (HMM)\nprovides a fundamental approach for unsupervised sequential labeling, the basic\nmodel …