VISUAL ATTENTION

Home database Miscalleanous

Eye tracking data for a set of pictures

A database containing the visual scan paths of different observers (up to 40) is available here (archive's size is less than 10Mo). A password is required, send me an e-mail and I will give you it (olemeur@irisa.fr).

Please cite the following paper in any published work if you use it:

O. Le Meur, P. Le Callet, D. Barba and D. Thoreau, A coherent computational approach to model the bottom-up visual attention, IEEE Pattern Analysis and Machine Intelligence, Vol. 28, N°5, May 2006. [pdf]

The proposed database is composed of:

• 27 color pictures. Some examples below:



• a text file for each picture. Each line of this file is the visual scan path of a given observer. A line is composed of a set of triplet indicating the coordinates of the fixation point and its duration (x y t). The end of the scanpath is given by (-1 -1 -1).

I will put a code source in order to build the experimental saliency maps. Below, some outputs of the code. From the left-hand side to the right: Heat Map, Highlight Map, Saliency Map and first most visually interesting points.(Click to get the full resolution picture.)




You can download all pictures (Heat map, Highlight, SM and WTA pictures for an average observer...) here (archive's size is less than 30Mo). A password is required (the same as previous one).

Miscalleanous

• ICIP 2009, special session: visual attention: models and applications in image and video processing. Presentations of the oral session (without video sequences...) are below:
  • O. Le Meur and P. Le Callet: What we see is most likely to be what matters: visual attention and applications, [pdf] [paper,pdf]
  • N. Bruce and P. Kornprobst: On the role of context in probabilistic models of visual saliency, [pdf]
  • Y. Li, Y. Zhou, L. Xu, X. Yang and J. Yang, Incremental sparse saliency detection, [pdf]
  • H. Liu and I. Heynderickx, Studying the added value of visual attention in objective image quality metrics based on eye movement data, presentation not yet available
  • C. Vu and D. Chandler, Main subject detection via adaptive feature selection, [pdf]
  • H. Liu, X. Qiu, Q. Huang, S. Jiang and C. Xu, Advertise gently in-image advertising with low intrusiveness, [pdf]
  • F. Boulos, W. Chen, B. Parrein and P. Le Callet, Region-of-interest intra prediction for H.264/AVC error resilience, [pdf]
  • N. Sadaka and L. Karam, Efficient perceptual attentive super-resolution, presentation not yet available