Modelling irregularly-sampled time series (ISTS) is challenging because ...
Nearest neighbor (NN) sampling provides more semantic variations than
pr...
Global contexts in images are quite valuable in image-to-image translati...
Many real-world applications based on online learning produce streaming ...
Image retrieval has garnered growing interest in recent times. The curre...
Coreset selection is among the most effective ways to reduce the trainin...
Fluorescence microscopy is a quintessential tool for observing cells and...
Traditional CNN models are trained and tested on relatively low resoluti...
Object trackers deployed on low-power devices need to be light-weight,
h...
Binarization has proven to be amongst the most effective ways of neural
...
Convolutional neural network (CNN) approaches available in the current
l...
Solving electromagnetic inverse scattering problems (ISPs) is challengin...
Streaming classification methods assume the number of input features is ...
In many real-world scientific problems, generating ground truth (GT) for...
Learning to dehaze single hazy images, especially using a small training...
The recent worldwide outbreak of the novel corona-virus (COVID-19) opene...
Analyzing video for traffic categorization is an important pillar of
Int...
Learning to solve diagrammatic reasoning (DR) can be a challenging but
i...
This paper presents an iterative smoothing technique for polygonal
appro...
Performing a grasp is a pivotal capability for a robotic gripper. We pro...
Maritime vessels equipped with visible and infrared cameras can compleme...
This thesis presents important insights and concepts related to the topi...