Machine learning is an essential discipline in artificial intelligence & image processing
because it affects item/object or asset recognition or identification processes. It employs …

Recent advances in neural camera imaging pipelines have demonstrated notable progress.
Nevertheless, the real-world imaging pipeline still faces challenges including the lack of joint …

Quantifying a model's predictive uncertainty is essential for safety-critical applications such
as autonomous driving. We consider quantifying such uncertainty for multi-object detection …

In the field of internet of things (IoT), data distillation has been thought of as a key method to
condense the original real dataset into a tiny synthetic dataset with less training burden …

Dynamic models are indispensable for the optimization, prediction and control of thermal
comfort in buildings. This paper proposes a new method for modeling the nonlinear …

Computational color constancy is an under-determined problem. As such, a key objective is
to assign a level of uncertainty to the output illuminant estimations, which can significantly …

Explainable AI has brought transparency to complex ML black boxes, enabling us, in
particular, to identify which features these models use to make predictions. So far, the …

Learning from corrupted data marginally degrades model performance. As deep learning
proliferates, the need for large, accurately labeled datasets becomes crucial. Central to this …

While computer vision has proven valuable for medical image segmentation, its application
faces challenges such as limited dataset sizes and the complexity of effectively leveraging …

With the recent advancements in machine learning technology, the accuracy of autonomous
driving object detection models has significantly improved. However, due to the complexity …