Artificial intelligence powered by deep neural networks has reached a level of complexity where it can be difficult or impossible to express how a model makes its decisions. This …
Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual …
Y Tang, D Nguyen, D Ha - Proceedings of the 2020 Genetic and …, 2020 - dl.acm.org
Inattentional blindness is the psychological phenomenon that causes one to miss things in plain sight. It is a consequence of the selective attention in perception that lets us remain …
We present a new end-to-end network architecture for facial expression recognition with an attention model. It focuses attention in the human face and uses a Gaussian space …
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 …
AJE Kell, JH McDermott - Current opinion in neurobiology, 2019 - Elsevier
Highlights•Deep neural networks (DNNs) now reach human-level performance on some perceptual tasks.•They show human-like error patterns and predict sensory cortical …
A Francl, JH McDermott - Nature human behaviour, 2022 - nature.com
Mammals localize sounds using information from their two ears. Localization in real-world conditions is challenging, as echoes provide erroneous information and noises mask parts …
B Zhong, B Bai, J Li, Y Zhang… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
A class-agnostic tracker typically consists of three key components, ie, its motion model, its target appearance model, and its updating strategy. However, most recent top-performing …
A Deza, T Konkle - arXiv preprint arXiv:2006.07991, 2020 - arxiv.org
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 …