Mechanisms of top-down attention.

By F. Baluch, Laurent Itti. 2011

441 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

Citations in the corpus

Top-Down Neural Attention by Excitation Backprop (2016, background): “There is a rich literature about modeling the top-down influences on selective attention in the human visual system (see Baluch and Itti (2011) for a review).”
A Feedback Model of Attention Explains the Diverse Effects of Attention on Neural Firing Rates and Receptive Field Structure (2016, background): “For example, the pulvinar thalamic nucleus contains multiple maps that receive overlapping projections from hierarchically adjacent cortical areas, and has been implicated in attentional processing [29,39].”
State-of-the-Art in Visual Attention Modeling (2013, background): “Reviews of attention models from psychological, neurobiological, and computational perspectives can be found in [9], [77], [10], [12], [202], [204], [224].”
Biological underpinnings for lifelong learning machines (2022, background): “A top-down task-driven path can effectively direct attention to task-relevant features 97 , where it can 224,225 for experimental data). b , During sleep and rest following active behaviour (and sometimes during brief pauses in active behaviour 224 ), the hippocampal LFP shows ‘ripple’ activity…”
Attentional Pooling for Action Recognition (2017, unknown): “Instead, we choose to distinctly model class-speciﬁc “top-down” attention [3, 48, 59] from bottom-up visual saliency that is class-agnostic [37].”
Attention, learning and the value of information (2012, background): “Or, alternatively, does the top-down feedback carry higher bandwidth information regarding both stimuli and actions, conveyed by neurons with combined responses (Baluch and Itti, 2011)?”
Neurochemistry of Visual Attention (2021, background): “At the same time, the PFC is assumed to be essential for the top-down regulation of attention through long-range projections upon visual areas (Baluch and Itti, 2011; Noudoost and Moore, 2011; Paneri and Gregoriou, 2017).”
Channel Expansion Convolutional Network for Image Classification (2020, background): “Attention models are usually divided into three types: bottom-up attention models [9], [10], top-down attention models [11], [12], top-down and bottom-up attention models [13], [14].”