Detection of Activities and Events without Explicit Categorization

• Item type: Trans(1)
• 公開日: 2013-08-21
• タイトル: Detection of Activities and Events without Explicit Categorization
• タイトル / 言語: en
• タイトル: Detection of Activities and Events without Explicit Categorization
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [オリジナル論文] event detection, direct density-ratio estimation, cubic higher-order local auto-correlation
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Graduate School of Science and Engineering, Tokyo Institute of Technology／CANON Inc.
• 著者所属: CANON Inc.
• 著者所属: Graduate School of Information Science and Engineering, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Graduate School of Science and Engineering, Tokyo Institute of Technology / CANON Inc.
• 著者所属(英): en
• 著者所属(英): CANON Inc.
• 著者所属(英): en
• 著者所属(英): Graduate School of Information Science and Engineering, Tokyo Institute of Technology
• 著者名: Masao, Yamanaka; Masakazu, Matsugu; Masashi, Sugiyama
• 著者名(英): Masao, Yamanaka; Masakazu, Matsugu; Masashi, Sugiyama
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: We propose a method of unsupervised event detection from a video that compares probability distributions of past and current video sequence data in a sequential and hierarchical way. Because estimation of probability distributions is known to be difficult, naively comparing probability distributions via probability distribution estimation tends to be unreliable in practice. To cope with this problem, we use the state-of-the-art machine learning technique called density ratio estimation: The ratio of probability densities is directly estimated without density estimation, and thus probability distributions can be compared in a reliable way. Through experiments on a walking scene and a tennis match, we demonstrate the usefulness of the proposed approach.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: We propose a method of unsupervised event detection from a video that compares probability distributions of past and current video sequence data in a sequential and hierarchical way. Because estimation of probability distributions is known to be difficult, naively comparing probability distributions via probability distribution estimation tends to be unreliable in practice. To cope with this problem, we use the state-of-the-art machine learning technique called density ratio estimation: The ratio of probability densities is directly estimated without density estimation, and thus probability distributions can be compared in a reliable way. Through experiments on a walking scene and a tennis match, we demonstrate the usefulness of the proposed approach.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11464803
• 書誌情報: 情報処理学会論文誌数理モデル化と応用（TOM）; 巻 6, 号 2, p. 86-92, 発行日 2013-08-21
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7780
• 出版者 / 言語: ja
• 出版者: 情報処理学会