| Presentation | 2000/3/21 Actor/Actress Annotation for Drama Videos Using Face Space Clustering Shin'ichi Satoh, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper addresses to achieve an automated actor/actress annotation system for drama videos. Since face information is crucial in drama videos, extracting and identifying actors/actresses enables vaeious advanced multimedia applications such as a content-based video retrieval system. Manual annotation is ideal for high-quality drama video annotation, however, it is intractable to manually annotate thousands of face sequences of hours of drama videos. In order to circumvent this problem, semi-automated drama video annotation system is developed, which learns association of faces to names from only dozens of manually annotated face sequences and automatically annotates other face sequences. The system employs face sequence extraction and matching methods applicable to actual drama video as key technologies. Experimental results show that the system achieves around 70% accuracy in annotating about 700 face sequences using 40 manual annotations as the training set. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Video analysis / Video indexing / Pattern classification / Face recognition |
| Paper # | AI99-93,KBSE99-52 |
| Date of Issue |
| Conference Information | |
| Committee | KBSE |
|---|---|
| Conference Date | 2000/3/21(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 | Knowledge-Based Software Engineering (KBSE) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Actor/Actress Annotation for Drama Videos Using Face Space Clustering |
| Sub Title (in English) | |
| Keyword(1) | Video analysis |
| Keyword(2) | Video indexing |
| Keyword(3) | Pattern classification |
| Keyword(4) | Face recognition |
| 1st Author's Name | Shin'ichi Satoh |
| 1st Author's Affiliation | National Center for Science Information Systems(NACSIS)() |
| Date | 2000/3/21 |
| Paper # | AI99-93,KBSE99-52 |
| Volume (vol) | vol.99 |
| Number (no) | 719 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |