The Dynamic Representation of Scenes

By Ronald A. Rensink. 2000

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Attention on Attention for Image Captioning (2019, methodology): “The attention mechanism [32, 9], which is derived from human intuition, has been widely applied and yielded significant improvements for various sequence learning tasks.”
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention (2015, background): “Rather than compress an entire image into a static representation, attention allows for salient features to dynamically come to the forefront as needed.”
Recurrent Models of Visual Attention (2014, background): “Instead humans focus attention selectively on parts of the visual space to acquire information when and where it is needed, and combine information from different fixations over time to build up an internal representation of the scene [18], guiding future eye movements and decision making.”
Human Attention in Visual Question Answering: Do Humans and Deep Networks look at the same regions? (2016, background): “Humans have the ability to quickly perceive a scene by selectively attending to parts of the image instead of processing the whole scene in its entirety (Rensink, 2000).”
BAM: Bottleneck Attention Module (2018, background): “A number of studies [8, 24, 38] have shown that attention plays an important role in human perception.”
Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer (2016, methodology): “Early work on attention based tracking Larochelle & Hinton (2010), Denil et al. (2012) was motivated by human attention mechanism theories Rensink (2000) and was done via Restricted Bolz-mann Machines.”
CBAM: Convolutional Block Attention Module (2018, background): “It is well known that attention plays an important role in human perception [23,24,25].”
Action Recognition using Visual Attention (2015, background): “s attention depending on the scene and the action being performed. 1 INTRODUCTION It has been noted in visual cognition literature that humans do not focus their attention on an entire scene at once (Rensink, 2000). Instead, they focus sequentially on different parts of the scene to extract relevant”
Learning Where to Attend with Deep Architectures for Image Tracking (2011, background): “Humans track and recognize objects effortlessly and efﬁciently, exploiting attentional mechanisms (Rensink, 2000; Colombo, 2001) to cope with the vast stream of data.”
Spatially Adaptive Computation Time for Residual Networks (2016, background): “A natural way to tackle this issue is by using attention to guide the computation, which is similar to how biological vision systems operate [35].”
Deep Multimodal Representation Learning: A Survey (2019, background): “Rather than using all of the information at once, the attention decision process prefers to concentrate on the part of the scene selectively which is needed [151].”
Visual memory for natural scenes: Evidence from change detection and visual search (2006, methodology): “Further, the coherence field (the nexus plus the stabilized proto-objects) directly maps onto VSTM (Rensink, 2000).”
SNIPER: Efficient Multi-Scale Training (2018, background): “Naturally, it is difficult for us to focus on objects of different scales simultaneously [27].”
Distract Your Attention: Multi-Head Cross Attention Network for Facial Expression Recognition (2021, background): “Attention mechanism plays an important role in visual perception [6,37].”
Attention and choice: a review on eye movements in decision making. (2013, background): “Although most saliency models operate at a pixel level, and therefore ignore object representations, it has been argued that so-called ‘proto-objects’ might pertain to a mid-level system between bottom up and top down control (Rensink, 2000; Wischnewski, Belardinelli, Schneider, & Steil, 2010).”
Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network (2019, background): “Motivated by the human visual perception process [46], the attention mechanism is designed to focus more on the informative areas and takes less account of non-essential areas.”
“Important stuff, everywhere!” Activity recognition with salient proto-objects as context (2014, background): “But, how can we attend to objects before we recognize them [37]? Rensink introduced the concept of proto-objects in his coherence theory [30, 37] and defined them as volatile units of visual information that may be validated as actual objects through focused attention.”