A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised Learning of Finite Mixture Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Coherent Computational Approach to Model Bottom-Up Visual Attention
IEEE Transactions on Pattern Analysis and Machine Intelligence
2006 Special Issue: Modeling attention to salient proto-objects
Neural Networks
LabelMe: A Database and Web-Based Tool for Image Annotation
International Journal of Computer Vision
Assessing the contribution of color in visual attention
Computer Vision and Image Understanding - Special issue: Attention and performance in computer vision
Linear vs. nonlinear feature combination for saliency computation: a comparison with human vision
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Depth matters: influence of depth cues on visual saliency
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Proceedings of the 6th International Symposium on Visual Information Communication and Interaction
| Hi-index | 0.02 |
A purely bottom-up model of visual attention is proposed and compared to five state-of-the-art models. The role of the low-level visual features is examined in two contexts. Two datasets are used: one containing data coming from an eye tracking experiment obtained in a free-viewing task and a second containing 5000 hand-label pictures (observers had to enclose the most visually interesting objects in a rectangle). The relevance of the bottom-up models, i.e., the ability of a model to predict where the salient areas are located, is evaluated. Whatever the metrics and the datasets, the degree of similarity between predictions and ground truth is significantly above chance. The proposed model, resting on a small number of features, is shown to be a good predictor of the human visual fixations but also a good predictor of the objects chosen as interesting by observers. This study suggests that the low-level visual features have a significant role in a free-viewing task but also in a high-level visual task, such as the choice of the object of interest in a complex visual scene. Another outcome concerns the viewing duration used in eye tracking experiments. Results suggest that this parameter is finally not as critical as one would expect.