Sentence examples for fixation dataset from inspiring English sources

To evaluate our proposed method, we do extensive experiments on three well-known image data sets including MSRA image set, PASCAL VOC image set, and human fixation dataset.

The proposed method achieves a slightly higher ROC area than DSR and also outperforms the state-of-the-art methods on this human fixation dataset.

To perform a fair comparison, we use the fixation points provided by the dataset as the ground truth for all the compared methods, i.e., only the points are fixations and the rest are non-fixations.

Among the existing methods, the very recent method MR has the best fixation prediction performance on this dataset, whose ROC area is 0.7378.

In the dataset, 20 subjects' fixations are recorded for each image.

However, it can be seen that the ROC area of the proposed method is about 0.025 (3.4%) higher than MR. It demonstrates that the proposed method outperforms the 12 state-of-the-art methods on predicting human fixations on this eye tracking dataset.

Rather than comparing the saliency measures at attended locations in the current scene to the saliency measures at unattended locations in the same scene, we compared the saliency measures at the attended locations to the saliency measures in that scene at the locations that are attended in different scenes in the dataset, called shuffled fixations.

The results of the proposed method are shown in Figure 8n, and the fixation density maps provided in the dataset are given in Figure 8o.

As shown in Figure 1, the pen container is the most salient according to the fixation density map from the MIT-1003 dataset [23], which shows the region attracting the attention of most subjects.

Full descriptions of all the analytical methods for measuring H2 and N2 fixation and also the accompanying hydrographic datasets are in the Supporting Information (see Appendix S1).

This dataset supplies 2D and 3D fixation maps.