Matei Mancas1,2 Olivier Le Meur 2
1Faculté Polytechnique de Mons (FPMs), Belgium
2IRISA/univsersity of Rennes 1, France
ICIP (2013)
The image memorability consists in the faculty of an image to be recalled after a period of time. Recently, the memorability of an image database was measured and some factors responsible for this memorability were highlighted. In this paper, we investigate the role of visual attention in image memorability around two axis. The first one is experimental and uses results of eye-tracking performed on a set of images of different memorability scores. The second investigation axis is predictive and we show that attention-related features can advantageously replace low-level features in image memorability prediction. From our work it appears that the role of visual attention is important and should be more taken into account along with other low-level features.
Some examples (fixation and heat maps). Memorability of pictures: left:0.4;right:0.8
The dataset is composed of 135 pictures (3 classes of 45 pictures). Eye tracking data is also provided. The format is the one described [here] (see also the software which can be used to perform anlysis and heat/saliency map computation.
@CONFERENCE{Mancas2013, author = {Mancas, M. and Le Meur, O.}, title = {Memorability of natural scene: the role of attention}, booktitle= {ICIP}, year = {2013}, doi = {xx} }