| Presentation | 2012-02-10 Event Detection from Video Using GMM-Supervectors and SVMs Yusuke KAMISHIMA, Nakamasa INOUE, Koichi SHINODA, Shunsuke SATO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In multimedia event detection, complex target events are detected from a large set of consumer domain videos taken in unconstrained environment. We propose a multimedia event detection method using GMM supervectors and support vector machines (SVMs) with multiple features. A GMM supervector consists of the parameters of a Gaussian mixture model (GMM) which represents the distribution of local features extracted from a clip. GMMs can be regarded as an extension of the Bag-of-Words (BoW) method to a probabilistic framework, and thus, expected to be robust against the data insufficiency problem. In the experiment using the dataset of TRECVID2010 MED task, the performance of the proposed method (mean minimum NDC 0.534) was better than the conventional method based on BoW (0.565). |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Multimedia event detection / Feature extraction / GMM-Supervector / Support vector machine |
| Paper # | PRMU2011-230,SP2011-145 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2012/2/2(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Event Detection from Video Using GMM-Supervectors and SVMs |
| Sub Title (in English) | |
| Keyword(1) | Multimedia event detection |
| Keyword(2) | Feature extraction |
| Keyword(3) | GMM-Supervector |
| Keyword(4) | Support vector machine |
| 1st Author's Name | Yusuke KAMISHIMA |
| 1st Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology() |
| 2nd Author's Name | Nakamasa INOUE |
| 2nd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology |
| 3rd Author's Name | Koichi SHINODA |
| 3rd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology |
| 4th Author's Name | Shunsuke SATO |
| 4th Author's Affiliation | R&D Division, Canon Inc. |
| Date | 2012-02-10 |
| Paper # | PRMU2011-230,SP2011-145 |
| Volume (vol) | vol.111 |
| Number (no) | 430 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |