| Presentation | 2014-12-18 A Hybrid Systems Approach to Modeling and Learning Multimedia Timing Structures Hiroaki KAWASHIMA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Capturing dynamic events of human body motion, facial action, and speech, via sensors, e.g., cameras and microphones, we can obtain a variety of temporal data. To model and analyze the dynamics of captured targets from the data, we introduce a method to utilize "hybrid systems." We here use a particular model of hybrid systems that switches several dynamical systems by the upper-level discrete-event system (automaton). If target dynamics can be represented by a set of simple primitives, a model-based clustering algorithm can automatically segment and estimate each of the primitive dynamic models. Besides, an identified model can generate signals similar to given training data. In this report, we show some applications that utilize these features, such as facial-expression analysis and multimedia timing modeling. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Hybrid system / linear dynamical system / timing / facial expression / audio-visual integration |
| Paper # | SIS2014-78 |
| Date of Issue |
| Conference Information | |
| Committee | SIS |
|---|---|
| Conference Date | 2014/12/11(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 | Smart Info-Media Systems (SIS) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Hybrid Systems Approach to Modeling and Learning Multimedia Timing Structures |
| Sub Title (in English) | |
| Keyword(1) | Hybrid system |
| Keyword(2) | linear dynamical system |
| Keyword(3) | timing |
| Keyword(4) | facial expression |
| Keyword(5) | audio-visual integration |
| 1st Author's Name | Hiroaki KAWASHIMA |
| 1st Author's Affiliation | Graduate School of Informatics, Kyoto University() |
| Date | 2014-12-18 |
| Paper # | SIS2014-78 |
| Volume (vol) | vol.114 |
| Number (no) | 370 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |