When looking at a visual scene, we focalize our attention and our gaze on particular regions of this scene, called salient regions, in order to analyze these regions more precisely. The purpose of this thesis was to better understand the attentional processes that guide our gaze when viewing a video and to model these processes. Two complementary approaches have been used: a behavioral one, using eyetracking experiments, which aims at analysing how subjects gazed at a video and a modelling approach leading to a model, biologically inspired, highlighting the salient regions in videos. Two models have been proposed. The rst saliency model, with two pathways, that extracts the static and the dynamic features from luminance and motion informati...
AbstractTo what extent can a computational model of the bottom–up visual attention predict what an o...
International audienceTo what extent can a computational model of the bottom–up visual attention pre...
Regions in video streams attracting human interest contribute significantly to human understanding o...
When looking at a visual scene, we focalize our attention and our gaze on particular regions of this...
The studies conducted in this thesis focus on the role of colour in visual attention. We tried to un...
Studies conducted in this thesis focuses on faces and visual attention. We are interested to better ...
Human vision system actively seeks salient regions and movements in video sequences to reduce the se...
International audienceThis paper presents a spatio-temporal saliency model that predicts eye movemen...
The evaluation of the features of an image analysing the eye movements is important for developing c...
ACM, (2012). This is the authors version of the work. It is posted here by permission of ACM for you...
In this thesis, we focus on understanding human behavior from gaze information. In contrast to stati...
Human visual system actively seeks salient regions and movements in video sequences to reduce the se...
This paper presents a spatio-temporal saliency model that pre-dicts eye movements. This biologically...
pp 508-513International audienceWhen viewing video sequences, the human visual system (HVS) tends to...
Abstract — Since visual attention-based computer vision appli-cations have gained popularity, ever m...
AbstractTo what extent can a computational model of the bottom–up visual attention predict what an o...
International audienceTo what extent can a computational model of the bottom–up visual attention pre...
Regions in video streams attracting human interest contribute significantly to human understanding o...
When looking at a visual scene, we focalize our attention and our gaze on particular regions of this...
The studies conducted in this thesis focus on the role of colour in visual attention. We tried to un...
Studies conducted in this thesis focuses on faces and visual attention. We are interested to better ...
Human vision system actively seeks salient regions and movements in video sequences to reduce the se...
International audienceThis paper presents a spatio-temporal saliency model that predicts eye movemen...
The evaluation of the features of an image analysing the eye movements is important for developing c...
ACM, (2012). This is the authors version of the work. It is posted here by permission of ACM for you...
In this thesis, we focus on understanding human behavior from gaze information. In contrast to stati...
Human visual system actively seeks salient regions and movements in video sequences to reduce the se...
This paper presents a spatio-temporal saliency model that pre-dicts eye movements. This biologically...
pp 508-513International audienceWhen viewing video sequences, the human visual system (HVS) tends to...
Abstract — Since visual attention-based computer vision appli-cations have gained popularity, ever m...
AbstractTo what extent can a computational model of the bottom–up visual attention predict what an o...
International audienceTo what extent can a computational model of the bottom–up visual attention pre...
Regions in video streams attracting human interest contribute significantly to human understanding o...