Researchers are defining new types of interactions between humans and machine learning
algorithms generically called human-in-the-loop machine learning. Depending on who is in …

Curriculum learning (CL) is a training strategy that trains a machine learning model from
easier data to harder data, which imitates the meaningful learning order in human curricula …

Training machine learning models in a meaningful order, from the easy samples to the hard
ones, using curriculum learning can provide performance improvements over the standard …

Effective strategies to restrain COVID-19 pandemic need high attention to mitigate
negatively impacted communal health and global economy, with the brim-full horizon yet to …

Neural sequence models are widely used to model time-series data. Equally ubiquitous is
the usage of beam search (BS) as an approximate inference algorithm to decode output …

We propose a novel framework for abnormal event detection in video that requires no
training sequences. Our framework is based on unmasking, a technique previously used for …

A single image captures the appearance and position of multiple entities in a scene as well
as their complex interactions. As a consequence, natural language grounded in visual …

We propose a novel knowledge distillation framework for effectively teaching a sensorimotor
student agent to drive from the supervision of a privileged teacher agent. Current distillation …

There are mainly two types of state-of-the-art object detectors. On one hand, we have two-
stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or …

Open set recognition (OSR) assumes unknown instances appear out of the blue at the
inference time. The main challenge of OSR is that the response of models for unknowns is …