| Item type |
SIG Technical Reports(1) |
| 公開日 |
2018-05-03 |
| タイトル |
|
|
タイトル |
Linking videos and languages: Representations and Their Applications |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Linking videos and languages: Representations and Their Applications |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
D論セッション2 |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
CyberAgent, Inc. |
| 著者所属 |
|
|
|
Osaka University |
| 著者所属 |
|
|
|
Tampere University of Technology |
| 著者所属 |
|
|
|
University of Oulu |
| 著者所属 |
|
|
|
Nara Institute of Science and Technology |
| 著者所属(英) |
|
|
|
en |
|
|
CyberAgent, Inc. |
| 著者所属(英) |
|
|
|
en |
|
|
Osaka University |
| 著者所属(英) |
|
|
|
en |
|
|
Tampere University of Technology |
| 著者所属(英) |
|
|
|
en |
|
|
University of Oulu |
| 著者所属(英) |
|
|
|
en |
|
|
Nara Institute of Science and Technology |
| 著者名 |
Mayu, Otani
Yuta, Nakashima
Esa, Rahtu
Janne, Heikkilä
Naokazu, Yokoya
|
| 著者名(英) |
Mayu, Otani
Yuta, Nakashima
Esa, Rahtu
Janne, Heikkilä
Naokazu, Yokoya
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Mimicking the human ability to understand visual data (images or videos) is a long-standing goal of computer vision. To achieve visual content understanding in a computer, many recent works attempt to connect visual and natural language data including object labels and descriptions. This attempt is important not only for visual understanding but also for broad applications such as content-based visual data retrieval and automatic description generation to help visually impaired people. The goal of this paper is to develop cross-modal representations, which enable us to associate videos with natural language. We explorer two directions for constructing cross-modal representations: hand-crafted representations and data-driven representation learning. The experiments demonstrate the proposed representations can be applied to a wide range of practical applications including query-focused video summarization and content-based video retrieval with natural language queries. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Mimicking the human ability to understand visual data (images or videos) is a long-standing goal of computer vision. To achieve visual content understanding in a computer, many recent works attempt to connect visual and natural language data including object labels and descriptions. This attempt is important not only for visual understanding but also for broad applications such as content-based visual data retrieval and automatic description generation to help visually impaired people. The goal of this paper is to develop cross-modal representations, which enable us to associate videos with natural language. We explorer two directions for constructing cross-modal representations: hand-crafted representations and data-driven representation learning. The experiments demonstrate the proposed representations can be applied to a wide range of practical applications including query-focused video summarization and content-based video retrieval with natural language queries. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA11131797 |
| 書誌情報 |
研究報告コンピュータビジョンとイメージメディア（CVIM）
巻 2018-CVIM-212,
号 38,
p. 1-16,
発行日 2018-05-03
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8701 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-CVIM18212038.pdf (5.7 MB)
