| Presentation | 2009-05-28 The Method of metadata extraction by categorizing feature data of contents on Video sharing sites Satoshi KONDOH, Junichi AKAHANI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently, multi-media Web-services including video sharing sites have become popular. And a lot of research that applies data acquired from devices such as cameras and microphones to context aware services is being performed in the fields of Life-Log and sensor networks. On the other hand, the common platform that can collect context data from any users' terminals and enable developers to make profitable service easily is needed. A variety of analytical techniques has been proposed for recognizing various patterns in the raw data because video and audio data include a larger volume of information than other sensor data. However, watching in person a huge amount of media data has been necessary to create training data for pattern learning. In addition, those techniques were not suitable for processing with the server because the processing load is large. Thus, we proposed a method of acquiring supervised data from a video sharing site where users can make comments on any video clip because various comments are generated. However, our conventional method recognized wrong results when the system gets media data that is different from the training media data. In this paper, we proposed the improvement technique that can recognize the appropriate results in the partial feature space by categorizing the feature data. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Metadata / Pattern Recognition / Stream Processing |
| Paper # | IE2009-19,PRMU2009-10,MI2009-10 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2009/5/21(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) | The Method of metadata extraction by categorizing feature data of contents on Video sharing sites |
| Sub Title (in English) | |
| Keyword(1) | Metadata |
| Keyword(2) | Pattern Recognition |
| Keyword(3) | Stream Processing |
| 1st Author's Name | Satoshi KONDOH |
| 1st Author's Affiliation | NTT Network Service Systems Laboratories, NTT Corporation() |
| 2nd Author's Name | Junichi AKAHANI |
| 2nd Author's Affiliation | NTT Network Service Systems Laboratories, NTT Corporation |
| Date | 2009-05-28 |
| Paper # | IE2009-19,PRMU2009-10,MI2009-10 |
| Volume (vol) | vol.109 |
| Number (no) | 64 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |