Abstract
The knowledge of where a person is looking is useful in human computer interaction as well as human behavior analysis. Headpose estimation from low resolution images is still a challenge problem due to noisy feature representation for low resolution images. In this paper, we investigate transfer learning technique to conquer the weakness of the apperance-based feature of humans head-pose when their relative locations to far-field cameras are different. We evaluate our methods on public datasets which prove the efficiency of our proposed method.
Similar content being viewed by others
References
APerez, Cordoba M (2003) A precise eye-gaze detection and tracking system. In: Proc Intl Conf. on Computer Graphics, Visualization and Computer Vision
Argyrious A, Evegenious T (2007) Multi-task feature learning. In: NIPS
Ba O, Odobez J (2005) Evaluation of multiple cues head pose estimation algorithms in natural environments. In: Proc. of the Intl. Conf. on Multi-media and Expo
Ba O, Odobez J (2011) Multiperson visual focus of attention from head pose and meeting contextual cues. In: IEEE Transactions on Pattern Analysis and Machine Intelligence
Bonilla E, Chai K, Williams C (2008) Multi-task gaussian process prediction. In: NIPS
Chang CC, Lin CJ (2001) Libsvm: a library for support vector machines
Chutorian E M, Trivedi M M (2009) Head pose estimation in computer vision: a survey. In: IEEE Transations on Pattern Analysis and Machine Intelligence
Dai W, Yang Q, Yu Y (2007) Boosting for transfer learning. In: ICML
Daume H (2007) Frustratingly easy domain adaptation. In: Proc. of the Assoc. Computational Linguistics
Duan L, Tsang I W, Xu D, Maybank SJ (2009) Domain transfer svm for video concept detection. In: CVPR
Duan L, Xu D, Tsang IW, Luo J (2010) Visual event recognition in videos by learning from web data. In: CVPR
Evgeniou T, Pontil M (2004) Regularized multi-task learning. In: Proc. 10th ACM SIGKDD Int Conf. Knowledge Discovery and Data Mining
Evgenious T, Poggio T, Verri A (2002) Regularization and statistical learning theory for data analysis. Computational Statistics and Data Analysis 38:421–432
Freund Y, Schapire R (1999) A short introduction to boosting. Journal of Japanese Society for Artificial Intelligence 14(5):771–780
Gee A, Cipolla R (1994) Determining the gaze of faces in images, vol 12
Gretton A, Borgwardt K, Scholkopt B (2006) A kernel method for the two-sample-problem. In: NIPS
Huang J, Smola A, Scholkopf B (2007) Correcting sample selection bias by unlabeled data. In: NIPS
Jiang W, Zavesky E, Chang SF, Loui A (2008) Cross-domain learning methods for high-level visual concept classification. In: Proc. IEEE Int Conf. Image Processing, pp. 161164
Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Mihalkova L, Huynh T, Mooney R (2007) Mapping and revising markov logic networks for transfer learning. In: Proc. for the Advancement of Artificial Intelligence (AAAI) Conf. Artificial Intelligence
Orozco J, Gong S, Xiang T (2009) Head pose classification in crowded scenes. In: British Machine Vision Conference
Pan SJ, Yang Q (2010) A survey on transfer learning. In: IEEE Transactions on Knowledge and Data Engineering, Vol 22. NO 10
Pan SJ, Kwok JT, Yang Q (2008) Transfer learning via dimensionality reduction. In: Proc. Assoc. for the Advancement of Artificial Intelligence
Rakotomamonjy A, Bach FR (2008) Simplemkl. In: Journal of Machine Learning Research
Robertson N, Reid I (2006) Estimating gaze direction from low-resolution faces in video. In: Proc. European Conf. Computer Vision
Smith K, Ba O, Odobez J (2008) Tracking the visual focus of attention for a varying number of wandering people. In: IEEE Transactions on Pattern Analysis and Machine Intelligence
Sugiyama M, Nakajima S, Kawanabe M (2008) Direct importance estimation with model selection and its application to covariate shift adaptation. In: NIPS
Tosato D, Farenzena M, Cristani M (2010) Multi-class classification on riemannian manifolds for video surveillance. In: Proc. European Conf. Computer Vision
Tuzal O, Porikli F, Meer P (2008) Pedestrian detection via classification on riemannian manifolds. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(10):1713–1727
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: CVPR
Wu P (2004) Improving svm accuracy by training on auxiliary data sources. In: ICML
Yan Y, Subramanian R, Lanz O, Sebe N (2012) Active transfer learning for multi-view head-pose classification. In: ICPR
Yan Y, Ricci E, Subramanian R, Lanz O, Sebe N (2013) No matter where you are: Flexible graph-guided multi-task learning for multi-view head pose classification under target motion. In: ICCV
Yan Y, Ricci E, Subramanian R, Liu G, Sebe N (2014) Multi-task linear discriminant analysis for multi-view action recognition. IEEE Trans Image Process 23 (12):5599–5611
Yan Y, Ricci E, Liu G, Sebe N (2015) Egocentric daily activity recognition via multitask clustering. IEEE Transactions on Image Processing 24(10):2984–2995
Yan Y, Yang Y, Meng D, Liu G, Tong W, Hauptmann A, Sebe N (2015) Event oriented dictionary learning for complex event detection. IEEE Transactions on Image Processing 24(6):1867–1878
Yan Y, Ricci E, Subramanian R, Liu G (2016) A multi-task learning framework for head pose estimation under target motion. IEEE Transactions on Pattern Analysis and Machine Intelligence
Yang J, Yan R, Hauptmann AG (2007) Cross-domain video concept detection using adaptive svms. In: Proc. ACM Int Conf. Multimedia
Yao Y, Dorretto G (2010) Boosting for transfer learning with multiple sources. In: CVPR
Zheng VW, Pan SJ, Yang Q (2008) Transferring multi-device localization models using latent multi-task learning. In: Proc. Assoc. for the Advancement of Artificial Intelligence
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, P., Li, Y. & Tan, L. Transfer useful knowledge for headpose estimation from low resolution images. Multimed Tools Appl 75, 9395–9408 (2016). https://doi.org/10.1007/s11042-016-3297-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3297-2