For more than 100 years we have known that the visual field is mapped onto the surface of
visual cortex, imposing an inherently spatial reference frame on visual information …

Convolutional neural networks (CNNs) have become a classic approach to solving
challenging computer vision problems. Much of its success is due to its ability to discover …

The human visual system uses two parallel pathways for spatial processing and object
recognition. In contrast, computer vision systems tend to use a single feedforward pathway …

Context plays an important role in visual recognition. Recent studies have shown that visual
recognition networks can be fooled by placing objects in inconsistent contexts (eg, a cow in …

The goal of this work is to characterize the representational impact that foveation operations
have for machine vision systems, inspired by the foveated human visual system, which has …

Context is of fundamental importance to both human and machine vision; eg, an object in
the air is more likely to be an airplane than a pig. The rich notion of context incorporates …

Simple Summary To assist researchers in processing large amounts of bird image data,
many algorithms have been proposed, but almost all of them aim at solving the problems of …

Humans are extremely proficient at visually perceiving natural scenes and understanding
high level scene structures. In recent times, scene understanding is a challenging and most …

Deep neural networks have become the de facto choice as feature extraction engines,
ubiquitously used for computer vision tasks. The current approach is to process every input …

Deep learning systems frequently fail at out-of-context (OOC) prediction, the problem of
making reliable predictions on uncommon or unusual inputs or subgroups of the training …