@inproceedings{ borji_boosting_2012,
  title = {Boosting bottom-up and top-down visual features for saliency estimation},
  doi = {10.1109/CVPR.2012.6247706},
  abstract = {Despite significant recent progress, the best available visual saliency models still lag behind human performance in predicting eye fixations in free-viewing of natural scenes. Majority of models are based on low-level visual features and the importance of top-down factors has not yet been fully explored or modeled. Here, we combine low-level features such as orientation, color, intensity, saliency maps of previous best bottom-up models with top-down cognitive visual features (e.g., faces, humans, cars, etc.) and learn a direct mapping from those features to eye fixations using Regression, SVM, and AdaBoost classifiers. By extensive experimenting over three benchmark eye-tracking datasets using three popular evaluation scores, we show that our boosting model outperforms 27 state-of-the-art models and is so far the closest model to the accuracy of human model for fixation prediction. Furthermore, our model successfully detects the most salient object in a scene without sophisticated image processings such as region segmentation.},
  booktitle = {2012 {IEEE} {Conference} on {Computer} {Vision} and {Pattern} {Recognition} ({CVPR})},
  author = {Borji, A.},
  month = {June},
  year = {2012},
  note = {00047},
  pages = {438--445}
}

{"_id":"smqKq9RewjAao7KwQ","bibbaseid":"borji-boostingbottomupandtopdownvisualfeaturesforsaliencyestimation-2012","downloads":0,"creationDate":"2015-09-03T07:18:48.990Z","title":"Boosting bottom-up and top-down visual features for saliency estimation","author_short":["Borji, A."],"year":2012,"bibtype":"inproceedings","biburl":"http://bibbase.org/zotero/fred.qi","bibdata":{"abstract":"Despite significant recent progress, the best available visual saliency models still lag behind human performance in predicting eye fixations in free-viewing of natural scenes. Majority of models are based on low-level visual features and the importance of top-down factors has not yet been fully explored or modeled. Here, we combine low-level features such as orientation, color, intensity, saliency maps of previous best bottom-up models with top-down cognitive visual features (e.g., faces, humans, cars, etc.) and learn a direct mapping from those features to eye fixations using Regression, SVM, and AdaBoost classifiers. By extensive experimenting over three benchmark eye-tracking datasets using three popular evaluation scores, we show that our boosting model outperforms 27 state-of-the-art models and is so far the closest model to the accuracy of human model for fixation prediction. Furthermore, our model successfully detects the most salient object in a scene without sophisticated image processings such as region segmentation.","author":["Borji, A."],"author_short":["Borji, A."],"bibtex":"@inproceedings{ borji_boosting_2012,\n title = {Boosting bottom-up and top-down visual features for saliency estimation},\n doi = {10.1109/CVPR.2012.6247706},\n abstract = {Despite significant recent progress, the best available visual saliency models still lag behind human performance in predicting eye fixations in free-viewing of natural scenes. Majority of models are based on low-level visual features and the importance of top-down factors has not yet been fully explored or modeled. Here, we combine low-level features such as orientation, color, intensity, saliency maps of previous best bottom-up models with top-down cognitive visual features (e.g., faces, humans, cars, etc.) and learn a direct mapping from those features to eye fixations using Regression, SVM, and AdaBoost classifiers. By extensive experimenting over three benchmark eye-tracking datasets using three popular evaluation scores, we show that our boosting model outperforms 27 state-of-the-art models and is so far the closest model to the accuracy of human model for fixation prediction. Furthermore, our model successfully detects the most salient object in a scene without sophisticated image processings such as region segmentation.},\n booktitle = {2012 {IEEE} {Conference} on {Computer} {Vision} and {Pattern} {Recognition} ({CVPR})},\n author = {Borji, A.},\n month = {June},\n year = {2012},\n note = {00047},\n pages = {438--445}\n}","bibtype":"inproceedings","booktitle":"2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":"10.1109/CVPR.2012.6247706","id":"borji_boosting_2012","key":"borji_boosting_2012","month":"June","note":"00047","pages":"438--445","title":"Boosting bottom-up and top-down visual features for saliency estimation","type":"inproceedings","year":"2012","bibbaseid":"borji-boostingbottomupandtopdownvisualfeaturesforsaliencyestimation-2012","role":"author","urls":{},"downloads":0},"search_terms":["boosting","bottom","top","down","visual","features","saliency","estimation","borji"],"keywords":[],"authorIDs":[],"dataSources":["y8en6y5RHukfeLuPH"]}