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.

Original languageEnglish
Title of host publicationProceedings of the Group Interaction Frontiers in Technology, GIFT 2018
EditorsSidney D'Mello , Stefan Scherer , Panayiotis (Panos) Georgiou
Place of PublicationNew York, NY, USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages8
ISBN (Electronic)978-145036077-7
Publication statusPublished - 2018
Event2018 Workshop on Group Interaction Frontiers in Technology, GIFT 2018 - Boulder, United States
Duration: 16 Oct 201816 Oct 2018


Conference2018 Workshop on Group Interaction Frontiers in Technology, GIFT 2018
CountryUnited States

    Research areas

  • Head and Body pose estimation, Matrix completion

ID: 52181696