Print Email Facebook Twitter Improving temporal interpolation of head and body pose using Gaussian process regression in a matrix completion setting Title Improving temporal interpolation of head and body pose using Gaussian process regression in a matrix completion setting Author Tan, S. (TU Delft Pattern Recognition and Bioinformatics) Tax, D.M.J. (TU Delft Pattern Recognition and Bioinformatics) Hung, H.S. (TU Delft Pattern Recognition and Bioinformatics) Contributor D'Mello, Sidney (editor) Scherer, Stefan (editor) Georgiou, Panayiotis (Panos) (editor) Date 2018 Abstract This paper presents a model for head and body pose estimation (HBPE) when labelled samples are highly sparse. The current state-of-the-art multimodal approach to HBPE utilizes the matrix completion method in a transductive setting to predict pose labels for unobserved samples. Based on this approach, the proposed method tackles HBPE when manually annotated ground truth labels are temporally sparse. We posit that the current state of the art approach oversimplifies the temporal sparsity assumption by using Laplacian smoothing. Our final solution uses: i) Gaussian process regression in place of Laplacian smoothing, ii) head and body coupling, and iii) nuclear norm minimization in the matrix completion setting. The model is applied to the challenging SALSA dataset for benchmark against the state-of-the-art method. Our presented formulation outperforms the state-of-the-art significantly in this particular setting, e.g. at 5% ground truth labels as training data, head pose accuracy and body pose accuracy is approximately 62% and 70%, respectively. As well as fitting a more flexible model to missing labels in time, we posit that our approach also loosens the head and body coupling constraint, allowing for a more expressive model of the head and body pose typically seen during conversational interaction in groups. This provides a new baseline to improve upon for future integration of multimodal sensor data for the purpose of HBPE. Subject Head and Body pose estimationMatrix completion To reference this document use: http://resolver.tudelft.nl/uuid:556dfc45-251f-4cae-881e-be61d9a5af88 DOI https://doi.org/10.1145/3279981.3279982 Publisher Association for Computing Machinery (ACM), New York, NY, USA Embargo date 2022-04-08 ISBN 978-145036077-7 Source Proceedings of the Group Interaction Frontiers in Technology, GIFT 2018 Event 2018 Workshop on Group Interaction Frontiers in Technology, GIFT 2018, 2018-10-16, Boulder, United States Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2018 S. Tan, D.M.J. Tax, H.S. Hung Files PDF 3279981.3279982.pdf 8.53 MB Close viewer /islandora/object/uuid:556dfc45-251f-4cae-881e-be61d9a5af88/datastream/OBJ/view