Show Reference: "A Model of Saliency-Based Visual Attention for Rapid Scene Analysis"

A Model of Saliency-Based Visual Attention for Rapid Scene Analysis IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 11. (1998), pp. 1254-1259 by Laurent Itti, Christof Koch, Ernst Niebur
@article{itti-et-al-1998,
    abstract = {A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a computationally efficient manner, conspicuous locations to be analyzed in detail.},
    author = {Itti, Laurent and Koch, Christof and Niebur, Ernst},
    journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    keywords = {attention, visual},
    number = {11},
    pages = {1254--1259},
    posted-at = {2011-09-20 10:18:09},
    priority = {0},
    title = {A Model of {Saliency-Based} Visual Attention for Rapid Scene Analysis},
    url = {http://citeseer.ist.psu.edu/itti98model.html},
    volume = {20},
    year = {1998}
}

See the CiteULike entry for more info, PDF links, BibTex etc.

Neural responses in LGN to short and medium-to-long wavelengths of light are antagonistic in rodents and cats (in certain cells).

Buzás et al. found blue-ON-type cells in the cat LGN, but no blue-OFF cells.

Contrast sensitivity is an important feature of early visual processing.