Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/100739
Title: | Discriminative video pattern search for efficient action detection | Authors: | Yuan, Junsong Liu, Zicheng Wu, Ying |
Keywords: | Electrical and Electronic Engineering | Issue Date: | 2011 | Source: | Yuan,J., Liu, Z., & Wu,Y. (2011) Discriminative Video Pattern Search for Efficient Action Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 33, 1728-1743. | Series/Report no.: | IEEE transactions on pattern analysis and machine intelligence | Abstract: | Actions are spatiotemporal patterns. Similar to the sliding window-based object detection, action detection finds the reoccurrences of such spatiotemporal patterns through pattern matching, by handling cluttered and dynamic backgrounds and other types of action variations. We address two critical issues in pattern matching-based action detection: 1) the intrapattern variations in actions, and 2) the computational efficiency in performing action pattern search in cluttered scenes. First, we propose a discriminative pattern matching criterion for action classification, called naive Bayes mutual information maximization (NBMIM). Each action is characterized by a collection of spatiotemporal invariant features and we match it with an action class by measuring the mutual information between them. Based on this matching criterion, action detection is to localize a subvolume in the volumetric video space that has the maximum mutual information toward a specific action class. A novel spatiotemporal branch-and-bound (STBB) search algorithm is designed to efficiently find the optimal solution. Our proposed action detection method does not rely on the results of human detection, tracking, or background subtraction. It can handle action variations such as performing speed and style variations as well as scale changes well. It is also insensitive to dynamic and cluttered backgrounds and even to partial occlusions. The cross-data set experiments on action detection, including KTH, CMU action data sets, and another new MSR action data set, demonstrate the effectiveness and efficiency of the proposed multiclass multiple-instance action detection method. [This work was supported in part by the Nanyang Assistant Professorship to Dr. Junsong Yuan, the National Science Foundation grant IIS-0347877, IIS-0916607, and US Army Research Laboratory and the US Army Research Office under grant ARO W911NF-08-1-0504.] | URI: | https://hdl.handle.net/10356/100739 http://hdl.handle.net/10220/18133 |
ISSN: | 0162-8828 | DOI: | 10.1109/TPAMI.2011.38 | Schools: | School of Electrical and Electronic Engineering | Rights: | © 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: http://dx.doi.org/doi:10.1109/TPAMI.2011.38 . | Fulltext Permission: | open | Fulltext Availability: | With Fulltext |
Appears in Collections: | EEE Journal Articles |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Discriminative Video Pattern Search for Efficient Action Detection.pdf | 982.23 kB | Adobe PDF | View/Open |
Page view(s) 5
923
Updated on Mar 27, 2024
Download(s) 5
832
Updated on Mar 27, 2024
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.