Modeling the influence of task on attention.

By Vidhya Navalpakkam, Laurent Itti. Vision Research, 2005

720 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/23c48356fcfac23af35636a0af1c0f0654521f42

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion (2011, neutral): “[19–25].”
A Benchmark of Computational Models of Saliency to Predict Human Fixations (2012, methodology): “Navalpakkam and Itti [49], Elazary and Itti [20] and Gao et al. [22] use this approach.”
Task and context determine where you look. (2016, background): “Navalpakkam and Itti (2005) have proposed such a model in object detection.”
State-of-the-Art in Visual Attention Modeling (2013, background): “Navalpakkam and Itti [51] derived the optimal integration of cues (channels of the BU saliency model [14]) for detection of a target in terms of maximizing the signal-to-noise ratio of the target versus background.”
Scene context guides eye movements during visual search. (2006, background): “Other forms of control undoubtedly arise from the demands speciWc to a given task (Land & Hayhoe, 2001; Navalpakkam & Itti, 2005; Turano, Geruschat, & Baker, 2003).”
Breaking the Fourth Wall of Cognitive Science (2016, background): “Perhaps the information-search and communicative functions of gaze are unique, top-down contributors to the control of visual attention (e.g., Navalpakkam & Itti, 2005; Wolfe, 2007).”
Gaze allocation in natural stimuli: Comparing free exploration to head-fixed viewing conditions (2009, background): “Consequently, recent extensions of the saliency map include task specific information (Navalpakkam & Itti, 2005).”
Facilitation of return during scene viewing (2009, methodology): “…& Niebur, 2002; Rosenholtz, 1999) or supplement bottom-up information with top-down memory-based factors such as scene semantics or viewing task (Navalpakkam & Itti, 2005; Rao, Zelinsky, Hayhoe, & Ballard, 2002; Sun, Fisher, Wang, & Gomes, 2008; Torralba, 2003; Torralba, Oliva, Castelhano, &…”
Predicting the presuppositions of soft triggers (2011, methodology): “In doing so, I am inspired by studies in cognitive psychology and computational vision (e.g. Goldstein 2009; Itti and Koch 2001; Navalpakkam and Itti 2005, etc.).”
Computational visual attention systems and their cognitive foundations: A survey (2010, methodology): “Attention systems able to perform active search, as for example [Navalpakkam et al. 2005] or [Frintrop 2005], are likely to achieve a larger correspondence in such settings.”
Attention and choice: a review on eye movements in decision making. (2013, background): “…as the primary driver of attention in, for instance, natural tasks (Hayhoe, 2000; Hayhoe, Shrivastava, Mruczek, & Pelz, 2003; Land, Mennie, & Rusted, 1999), and has been implemented in computational models of visual attention (Navalpakkam & Itti, 2005; Sprague, Ballard, & Robinson, 2007).”
What do eyes reveal about the mind?: Algorithmic inference of search targets from fixations (2015, neutral): “Please see [1] [33] [78] [74] [57] [48] [47] [39] [5] for reviews.”
Best practices in eye tracking research. (2020, background): “And even if the stimuli are the same, when participants are performing different tasks, their eye movement behavior changes; the location and duration of people's eye movements change significantly when they receive different instructions (Henderson et al., 2013a; Kardan et al., 2015; Kardan et al.,”
Interesting objects are visually salient. (2008, background): “…visual locations, then recognize the identity as well as a number of properties of each candidate, and finally evaluate these against current behavioral goals, intentions, and preferences, so as to decide whether that object was interesting or not (Navalpakkam & Itti, 2005; Rensink, 2000)?”