Please use this identifier to cite or link to this item:
https://doi.org/10.1109/WMVC.2008.4544051
Title: | Space-time shapelets for action recognition | Authors: | Batra D. Chen T. Sukthankar R. |
Issue Date: | 2008 | Citation: | Batra D., Chen T., Sukthankar R. (2008). Space-time shapelets for action recognition. 2008 IEEE Workshop on Motion and Video Computing, WMVC : 4544051. ScholarBank@NUS Repository. https://doi.org/10.1109/WMVC.2008.4544051 | Abstract: | Recent works in action recognition have begun to treat actions as space-time volumes. This allows actions to be converted into 3-D shapes, thus converting the problem into that of volumetric matching. However, the special nature of the temporal dimension and the lack of intuitive volumetric features makes the problem both challenging and interesting. In a data-driven and bottom-up approach, we propose a dictionary of mid-level features called Space-Time Shapelets.1 This dictionary tries to characterize the space of local space-time shapes, or equivalently local motion patterns formed by the actions. Representing an action as a bag of these space-time patterns allows us to reduce the combinatorial space of these volumes, become robust to partial occlusions and errors in extracting spatial support. The proposed method is computationally efficient and achieves competitive results on a standard dataset [5]. | Source Title: | 2008 IEEE Workshop on Motion and Video Computing, WMVC | URI: | http://scholarbank.nus.edu.sg/handle/10635/146239 | ISBN: | 1424420008 9781424420001 |
DOI: | 10.1109/WMVC.2008.4544051 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.