Cross-View Action Recognition Over Heterogeneous Feature Spaces
نویسندگان
چکیده
منابع مشابه
Unlabelled 3D Motion Examples Improve Cross-View Action Recognition
(a) (b) Figure 1: (a) We exploit the visual similarity between mocap-generated trajectories (left) and dense trajectories (right) to improve cross-view action recognition. (b) For mocap-trajectories, we can easily obtain corresponding features (i.e., descriptors for trajectories that originate from the same 3D point) in two views. We use these pairs of features to learn the transformation funct...
متن کاملCross-View Action Recognition from Temporal Self-similarities
This paper concerns recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures across views. Building upon this key observation we develop an action descriptor that captures the structure of temporal similarities and dissimilarities within an action sequence. Despite this descriptor not being st...
متن کاملNonlinear Cross-View Sample Enrichment for Action Recognition
Advanced action recognition methods are prone to limited generalization performances when trained on insufficient amount of data. This limitation results from the high expense to label training samples and their insufficiency to capture enough variability due to viewpoint changes. In this paper, we propose a solution that enriches training data by transferring their features across views. The p...
متن کاملCross-View Action Recognition via a Transferable Dictionary Pair
Jingjing Zheng1 [email protected] Zhuolin Jiang2 [email protected] P. Jonathon Phillips3 [email protected] Rama Chellappa1 [email protected] 1 Department of Electrical and Computer Engineering and the Center for Automation Research, UMIACS University of Maryland College Park, MD, USA 2 UMIACS, University of Maryland College Park, MD, USA 3 National Institute of Standards an...
متن کاملSimilarity Searches in Heterogeneous Feature Spaces
Correlating event streams or development paths of observed behavior that involves disparate types of data is a common problem in many applications including biomedical and clinical diagnosis systems. We present a new formulation of the following dual problem: (a) given multiple event streams for which we have prior knowledge, specify a feature space with heterogeneous dissimilarity measures, an...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Image Processing
سال: 2015
ISSN: 1057-7149,1941-0042
DOI: 10.1109/tip.2015.2445293