Importance Annotation for VIP and UIUC Pascal Sentence Datasets

Importance Annotation for VIP and UIUC Pascal Sentence Datasets

The experimental results for the paper Assigning Relative Importance to Scene Elements in SIBGRAPI’2017 (link to the research page) were obtained using two datasets: VIP dataset and UIUC Pascal Sentence. Both datasets are associate to importance assignment researches and present a wide range of images containing multiple objects per image.

 

Data

In order to use both datasets on the paper Assigning Relative Importance to Scene Elements, it was necessary to generate importance annotations, since they are not provided along dataset images. In addition, the VIP dataset does not provide element (people) bounding boxes and so, it was necessary to annotate these elements before using this dataset. VIP boxes annotations are available in: vip_boxes. In order to allow the reproduction of the experiments, we also provide the boxes of the UIUC Pascal sentence dataset, available in: uiuc_boxes.

After that, users were asked to generate importance annotations for images of the VIP and UIUC and Pascal Sentence Databases. These annotations are available in: Importance Annotations

 

References

You should include the following reference if you use the importance annotations in your work:

Igor L. O. Bastos, William Robson Schwartz (2017): Assigning Relative Importance to Scene Elements. In: Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 1-8, 2017. (Type: Inproceeding | Links | BibTeX)

In addition, you should include the references of the papers that presented the image datasets:

  • VIP: C. S. Mathialagan, A. C. Gallagher, and D. Batra, “VIP: Finding Important People in Images.” in CVPR, 2015, pp. 4858–4866.
  • UIUC Pascal Sentence: C. Rashtchian, P. Young, M. Hodosh, and J. Hockenmaier, “Collecting Image Annotations using Amazon’s Mechanical Turk,” in Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon’s Mechanical Turk, ser. CSLDAMT ’10, 2010, pp. 139–147.