You are here
DPOSE download page
DPOSE dataset comes with 18 files (gzipped tar archives, one per subject, plus recordings of the empty room) of about 3 GB each. Every archive contains three synchronized image sequences (4 views) with head pose references. Timestamps of images and references are also available. Structure of the archives and file formats are described in the README file.
Disclaimer: DPOSE dataset can be used for research or academic purposes only. The dataset has been published along with the papers referenced below.
- Dataset: Subject-01 Subject-02 Subject-03 Subject-04 Subject-05 Subject-06 Subject-07 Subject-08 Subject-09 Subject-10 Subject-11 Subject-12 Subject-13 Subject-14 Subject-15 Subject-16 Subject-17 empty-room
- Calibration files for CAM 0 CAM 1 CAM 2 CAM 3 computed using checkerboard pattern and OpenCV
- c++ code to compute the image projection of a 3D point from DPOSE calibration files
- Tracking of the subjects - ground coordinates
- Head crops from the localization - described in our pami paper referenced below
- Additional 5-minute recording with 6 subjects: Sequence, Tracking of the subjects, Head crops from the localization (online 10/31/2017)
Y. Yan, E. Ricci, R. Subramanian, G. Liu, O. Lanz, Sebe N.: A Multi-task Learning Framework for Head Pose Estimation under Target Motion, in IEEE Transactions on Pattern Analysis and Machine Intelligence , 38(6):1070-1083, 2016
A.K. Rajagopal, R. Subramanian, E. Ricci, R.L. Vieriu, O. Lanz, R. Kalpathi, N. Sebe: Exploring Transfer Learning Approaches for Head Pose Classification from Multi-view Surveillance Images. International Journal of Computer Vision, Vol. 109, N. 1-2, pp. 146-167, 2014
Y. Yan, E. Ricci, R. Subramanian, O. Lanz, N. Sebe: No Matter Where You Are: Flexible Graph-guided Multi-task Learning for Multi-view Head Pose Classification Under Target Motion. International Conference on Computer Vision - ICCV, pp. 1177-1184, Sydney, Australia, 1-8 December 2013
A.K. Rajagopal, R. Subramanian, R.L. Vieriu, E. Ricci, O. Lanz, N. Sebe, K. Ramakrishnan: An Adaptation Framework for Head Pose Estimation in Dynamic Multi-view Scenarios. Asian Conference on Computer Vision - ACCV 2012, Daejeon, Korea, November 5-9, 2012