Please use this identifier to cite or link to this item:
|Title:||Activity recognition using dense long-duration trajectories||Authors:||Sun, J.
|Issue Date:||2010||Citation:||Sun, J., Mu, Y., Yan, S., Cheong, L.-F. (2010). Activity recognition using dense long-duration trajectories. 2010 IEEE International Conference on Multimedia and Expo, ICME 2010 : 322-327. ScholarBank@NUS Repository. https://doi.org/10.1109/ICME.2010.5583046||Abstract:||Current research on visual action/activity analysis has mostly exploited appearance-based static feature descriptions, plus statistics of short-range motion fields. The deliberate ignorance of dense, long-duration motion trajectories as features is largely due to the lack of mature mechanism for efficient extraction and quantitative representation of visual trajectories. In this paper, we propose a novel scheme for extraction and representation of dense, long-duration trajectories from video sequences, and demonstrate its ability to handle video sequences containing occlusions, camera motions, and nonrigid deformations. Moreover, we test the scheme on the KTH action recognition dataset , and show its promise as a scheme for general purpose long-duration motion description in realistic video sequences. © 2010 IEEE.||Source Title:||2010 IEEE International Conference on Multimedia and Expo, ICME 2010||URI:||http://scholarbank.nus.edu.sg/handle/10635/69154||ISBN:||9781424474912||DOI:||10.1109/ICME.2010.5583046|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Feb 14, 2020
WEB OF SCIENCETM
checked on Feb 6, 2020
checked on Feb 17, 2020
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.