文献の詳細
| 論文の言語 | 英語 |
|---|---|
| 著者 | Mizuki Matsubara, Joachim Folz, Takumi Toyama, Marcus Liwicki, Andreas Dengel, Koichi Kise |
| 論文名 | Extraction of Read Text for Automatic Video Annotation |
| 論文誌名 | UbiComp/ISWC'15 Adjunct Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable Computers |
| ページ | pp.849-856 |
| 発表場所 | Osaka, Japan |
| 査読の有無 | 有 |
| 発表の種類 | 口頭発表 |
| 年月 | 2015年9月 |
| 要約 | This paper presents an automatic video annotation method which utilizes the user臓��s reading behaviour. Using a wearable eye tracker, we identify the video frames where the user reads a text document and extract the sentences that have been read by him or her. The extracted sentences are used to annotate video segments which are taken from the user臓��s egocentric perspective. An advantage of the proposed method is that we do not require training data, which is often used by a video annotation method. We examined the accuracy of the proposed annotation method with a pilot study where the experiment participants drew an illustration reading a tutorial. The method achieved 64:5% recall and 30:8% precision. |
| DOI | 10.1145/2800835.2804333 |
- 次のファイルが利用可能です．
- BibTeX用エントリー
@InProceedings{Matsubara2015, author = {Mizuki Matsubara and Joachim Folz and Takumi Toyama and Marcus Liwicki and Andreas Dengel and Koichi Kise}, title = {Extraction of Read Text for Automatic Video Annotation}, booktitle = {UbiComp/ISWC'15 Adjunct Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable Computers}, year = 2015, month = sep, pages = {849--856}, DOI = {10.1145/2800835.2804333}, location = {Osaka, Japan} }