Max-margin adaptive model for complex video pattern recognition
| LEADER | caa a22 4500 | ||
|---|---|---|---|
| 001 | 605446717 | ||
| 003 | CHVBK | ||
| 005 | 20210128100128.0 | ||
| 007 | cr unu---uuuuu | ||
| 008 | 210128e20150101xx s 000 0 eng | ||
| 024 | 7 | 0 | |a 10.1007/s11042-014-2010-6 |2 doi |
| 035 | |a (NATIONALLICENCE)springer-10.1007/s11042-014-2010-6 | ||
| 245 | 0 | 0 | |a Max-margin adaptive model for complex video pattern recognition |h [Elektronische Daten] |c [Litao Yu, Jie Shao, Xin-Shun Xu, Heng Shen] |
| 520 | 3 | |a Patternrecognitionmodels are usually used in a variety of applications ranging from video concept annotation to event detection. In this paper we propose a new framework called the max-margin adaptive (MMA) model for complex video pattern recognition, which can utilize a large number of unlabeled videos to assist the model training. The MMA model considers the data distribution consistence between labeled training videos and unlabeled auxiliary ones from the statistical perspective by learning an optimal mapping function which also broadens the margin between positive labeled videos and negative labeled videos to improve the robustness of the model. The experiments are conducted on two public datasets including CCV for video object/event detection and HMDB for action recognition. Our results demonstrate that the proposed MMA model is very effective on complex video pattern recognition tasks, and outperforms the state-of-the-art algorithms. | |
| 540 | |a Springer Science+Business Media New York, 2014 | ||
| 690 | 7 | |a Video pattern recognition |2 nationallicence | |
| 690 | 7 | |a Max-margin adaptive model |2 nationallicence | |
| 690 | 7 | |a Event detection |2 nationallicence | |
| 700 | 1 | |a Yu |D Litao |u School of Information Technology and Electrical Engineering, The University of Queensland, 4072, Brisbane, QLD, Australia |4 aut | |
| 700 | 1 | |a Shao |D Jie |u Department of Computer Science, National University of Singapore, 117417, Singapore, Singapore |4 aut | |
| 700 | 1 | |a Xu |D Xin-Shun |u School of Computer Science and Technology, Shandong University, 250101, Jinan, Shandong, People's Republic of China |4 aut | |
| 700 | 1 | |a Shen |D Heng |u School of Information Technology and Electrical Engineering, The University of Queensland, 4072, Brisbane, QLD, Australia |4 aut | |
| 773 | 0 | |t Multimedia Tools and Applications |d Springer US; http://www.springer-ny.com |g 74/2(2015-01-01), 505-521 |x 1380-7501 |q 74:2<505 |1 2015 |2 74 |o 11042 | |
| 856 | 4 | 0 | |u https://doi.org/10.1007/s11042-014-2010-6 |q text/html |z Onlinezugriff via DOI |
| 898 | |a BK010053 |b XK010053 |c XK010000 | ||
| 900 | 7 | |a Metadata rights reserved |b Springer special CC-BY-NC licence |2 nationallicence | |
| 908 | |D 1 |a research-article |2 jats | ||
| 949 | |B NATIONALLICENCE |F NATIONALLICENCE |b NL-springer | ||
| 950 | |B NATIONALLICENCE |P 856 |E 40 |u https://doi.org/10.1007/s11042-014-2010-6 |q text/html |z Onlinezugriff via DOI | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Yu |D Litao |u School of Information Technology and Electrical Engineering, The University of Queensland, 4072, Brisbane, QLD, Australia |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Shao |D Jie |u Department of Computer Science, National University of Singapore, 117417, Singapore, Singapore |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Xu |D Xin-Shun |u School of Computer Science and Technology, Shandong University, 250101, Jinan, Shandong, People's Republic of China |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Shen |D Heng |u School of Information Technology and Electrical Engineering, The University of Queensland, 4072, Brisbane, QLD, Australia |4 aut | ||
| 950 | |B NATIONALLICENCE |P 773 |E 0- |t Multimedia Tools and Applications |d Springer US; http://www.springer-ny.com |g 74/2(2015-01-01), 505-521 |x 1380-7501 |q 74:2<505 |1 2015 |2 74 |o 11042 | ||