Grounded and Co-Referenced Characters

This web page provides access to the Dataset for Grounded and Co-Referenced Characters, introduced in our CVPR 2017 work "Generating Descriptions with Grounded and Co-Referenced People" [1]. Prior to accessing the data, please make sure to request access to the MPII Movie Description dataset. After that you can use the obtained username and password to access the data on this page. (If you have already requested access previously, you can use the same username/password here.)

When using this data, please cite the following publication:

[1]  Generating Descriptions with Grounded and Co-Referenced People, A. Rohrbach, M. Rohrbach, S. Tang, S. J. Oh and B. Schiele, CVPR 2017

@inproceedings{RohrbachCVPR2017,
TITLE = {Generating Descriptions with Grounded and Co-Referenced People},
AUTHOR = {Rohrbach, Anna and Rohrbach, Marcus and Tang, Siyu and Oh, Seong Joon and Schiele, Bernt},
YEAR = {2017},
BOOKTITLE = {30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)},
}