Global contexts in images are quite valuable in image-to-image translati...
Coreset selection is among the most effective ways to reduce the trainin...
Traditional CNN models are trained and tested on relatively low resoluti...
Physics-based optimization problems are generally very time-consuming,
e...
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...
Gradient based meta-learning methods are prone to overfit on the
meta-tr...
Convolutional Neural Networks(CNN) are inherently equivariant under
tran...
Structured pruning methods are among the effective strategies for extrac...
Occlusion is one of the most difficult challenges in object tracking to
...
Ambiguities in images or unsystematic annotation can lead to multiple va...
Designs generated by density-based topology optimization (TO) exhibit ja...
U-Net and its variants have been demonstrated to work sufficiently well ...
Updating the tracker model with adverse bounding box predictions adds an...
Autoencoders are neural network formulations where the input and output ...
A class of vision problems, less commonly studied, consists of detecting...
Multiresolution topology optimization (MTO) methods involve decoupling o...
Machine learning is currently a trending topic in various science and
en...
Rock physics models (RPMs) are used to estimate the elastic properties (...