Abstract
Action recognition is usually a central problem for many practical applications, such as video annotations, video surveillance and human computer interaction. Most action recognition approaches are based on localized spatio-temporal features that can vary significantly when the viewpoint changes. However, their performance rapidly drops when the viewpoints of the training and testing data are different. In this paper, we propose a transfer learning framework for view-invariant action recognition by the way of sharing image stitching feature among different views. Experimental results on multi-view action recognition IXMAS dataset demonstrate that our method produces remarkably good results and outperforms baseline methods.
Similar content being viewed by others
References
Chang X, Ma Z, Lin M, Yang Y, Hauptmann A (2017) Feature interaction augmented sparse learning for fast kinect motion detection. In: IEEE transactions on image processing
Chang X, Ma Z, Yang Y, Zeng Z (2017) Hauptmann AG Bi-level semantic representation analysis for multimedia event detection. In: IEEE transactions on cybernetics
Chang X, Nie F, Wang S, Yang Y, Zhou X, Zhang C (2017) Compound rank-k projections for bilinear analysis. In: IEEE transactions on neural networks and learning systems
Farhadi A, Tabrizi MK (2008) Learning to recognize activities from the wrong view point. In: ECCV
Huang CH, Yeh YR, Wang YCF (2012) Recognizing actions across cameras by exploring the correlated subspace. In: ECCV
Li B, Camps OI, Sznaier M (2012) Cross-view activity recognition using hankelets. In: CVPR
Li R, Zickler T (2012) Discriminative virtual views for cross-view action recognition. In: CVPR
Liu J, Shah M, Kuipers B, Savarese S (2011) Cross-view action recognition via view knowledge transfer. In: CVPR
Reddy K, Liu J, Shah M (2009) Incremental action recognition using feature tree. In: ICCV
Sugiyama M, Nakajima S, Kawanabe M (2008) Direct importance estimation with model selection and its application to covariate shift adaptation. In: NIPS
Tuzal O, Porikli F, Meer P (2008) Pedestrian detection via classification on riemannian manifolds. IEEE Trans Pattern Anal Mach Intell 30(10):1713–1727
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: CVPR
Weinland D, Boyer E, Ronfard R (2007) Action recognition from arbitrary views using 3d exemplars. In: ICCV
Weinland D, Ronfard R, Boyer E (2011) A survey of vision-based methods for action representation, segmentation and recognition. Comput Vis Image Underst 115:224–241
Wu X, Jia Y (2012) View-invariant action recognition using latent kernelized structural SVM. In: ECCV
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: IEEE international conference on computer vision
Yan Y, Ricci E, Subramanian R, Liu G, Sebe N (2014) Multitask linear discriminant analysis for view invariant action recognition. In: IEEE transactions on image processing
Yan Y, Xu C, Cai D, Corso J (2017) Weakly supervised actor-action segmentation via robust multi-task ranking. In: IEEE conference on computer vision and pattern recognition
Acknowledgements
This research is supported by the Scientific Research Project of Hunan Provincial Education Department, China. The research and application of UAV Aerial system based on image splicing using multiple cameras (Grant No. 16C1139).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, Y., Li, P., Lei, D. et al. Investigating image stitching for action recognition. Multimed Tools Appl 77, 3279–3286 (2018). https://doi.org/10.1007/s11042-017-5072-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-5072-4