Search Results for author:
Found 28 papers, 7 papers with code
Learning Event-Driven Video Deblurring and Interpolation
Event-based sensors, which have a response if the change of pixel intensity exceeds a triggering threshold, can capture high-speed motion with microsecond accuracy.
Learning to See in the Dark with Events
A detail enhancing branch is proposed to reconstruct day light-specific features from the domain-invariant representations in a residual manner, regularized by a ranking loss.
XTSFormer: Cross-Temporal-Scale Transformer for Irregular Time Event Prediction
Event prediction aims to forecast the time and type of a future event based on a historical event sequence.
SimFair: Physics-Guided Fairness-Aware Learning with Simulation Models
Fairness-awareness has emerged as an essential building block for the responsible use of artificial intelligence in real applications.
Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting
Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources.
Morphological Profiling for Drug Discovery in the Era of Deep Learning
Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field.
Spatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagery
The problem is challenging due to the sparse and noisy input labels, spatial uncertainty within the label inference process, and high computational costs associated with a large number of sample locations.
Uncertainty Quantification of Deep Learning for Spatiotemporal Data: Challenges and Opportunities
With the advancement of GPS, remote sensing, and computational simulations, large amounts of geospatial and spatiotemporal data are being collected at an increasing speed.
Deep Learning for Spatiotemporal Big Data: A Vision on Opportunities and Challenges
With advancements in GPS, remote sensing, and computational simulation, an enormous volume of spatiotemporal data is being collected at an increasing speed from various application domains, spanning Earth sciences, agriculture, smart cities, and public safety.
A Comprehensive Survey on Uncertainty Quantification for Deep Learning
To fill the gap, this paper presents a systematic taxonomy of UQ methods for DNNs based on the types of uncertainty sources (data uncertainty versus model uncertainty).
An Explainer for Temporal Graph Neural Networks
Given a time series on a graph to be explained, the framework can identify dominant explanations in the form of a probabilistic graphical model in a time period.
STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction
High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities.
Physics-informed machine learning
Spatio-Temporal Forecasting
+1
Spatiotemporal Data Mining: A Survey
Furthermore, it has a detailed survey of parallel formulations of spatiotemporal data mining.
Modeling Reservoir Release Using Pseudo-Prospective Learning and Physical Simulations to Predict Water Temperature
However, the information of released water flow is often not available for many reservoirs, which makes it difficult for data-driven models to capture the impact to downstream river segments.
Content-Noise Complementary Learning for Medical Image Denoising
In this study, we propose a simple yet effective strategy, the content-noise complementary learning (CNCL) strategy, in which two deep learning predictors are used to learn the respective content and noise of the image dataset complementarily.
Background-aware Classification Activation Map for Weakly Supervised Object Localization
In our B-CAM, two image-level features, aggregated by pixel-level features of potential background and object locations, are used to purify the object feature from the object-related background and to represent the feature of the pure-background sample, respectively.
Bayesian Statistics Guided Label Refurbishment Mechanism: Mitigating Label Noise in Medical Image Classification
BLRM utilizes maximum a posteriori probability (MAP) in the Bayesian statistics and the exponentially time-weighted technique to selectively correct the labels of noisy images.
A Survey on Spatial and Spatiotemporal Prediction Methods
With the advancement of GPS and remote sensing technologies, large amounts of geospatial and spatiotemporal data are being collected from various domains, driving the need for effective and efficient prediction methods.
ClickTrain: Efficient and Accurate End-to-End Deep Learning Training via Fine-Grained Architecture-Preserving Pruning
Moreover, compared with the state-of-the-art pruning-during-training approach, ClickTrain provides significant improvements both accuracy and compression ratio on the tested CNN models and datasets, under similar limited training time.
Deep Learning for Earth Image Segmentation based on Imperfect Polyline Labels with Annotation Errors
The performance of these models heavily relies on high-quality ground truth segment labels.
Semi-supervised Learning with the EM Algorithm: A Comparative Study between Unstructured and Structured Prediction
Semi-supervised learning aims to learn prediction models from both labeled and unlabeled samples.
Spatial Classification With Limited Observations Based On Physics-Aware Structural Constraint
These methods, however, assume that incomplete feature observations only happen on a small subset of samples, and thus cannot solve problems where the vast majority of samples have missing feature observations.
Deep Neural Network for 3D Surface Segmentation based on Contour Tree Hierarchy
In contrast, we propose to represent surface topological structure by a contour tree skeleton, which is a polytree capturing the evolution of surface contours at different elevation levels.
Flood Extent Mapping based on High Resolution Aerial Imagery and DEM: A Hidden Markov Tree Approach
In contrast, we recently proposed a novel machine learning model called geographical hidden Markov tree that integrates spectral features of pixels and topographic constraints from Digital Elevation Model (DEM) data (i. e., water flow directions) in a holistic manner.
Learning Event-Based Motion Deblurring
Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process.
Ranked #27 on
Image Deblurring
on GoPro
(using extra training data)
Recurrent U-net: Deep learning to predict daily summertime ozone in the United States
We used the model to evaluate recent trends in NO$_x$ emissions in the US and found that the trend in the EPA emission inventory produced the largest negative bias in MDA8 ozone between 2010-2016.
Mapping road safety features from streetview imagery: A deep learning approach
Each year, around 6 million car accidents occur in the U. S. on average.
Geographical Hidden Markov Tree for Flood Extent Mapping (With Proof Appendix)
Anisotropic spatial dependency is incorporated in the hidden class layer with a reverse tree structure.
