Skip to content
University of Maryland LibrariesDigital Repository at the University of Maryland
    • ログイン
    アイテム表示 
    •   ホーム
    • College of Computer, Mathematical & Natural Sciences
    • Computer Science
    • Technical Reports from UMIACS
    • アイテム表示
    •   ホーム
    • College of Computer, Mathematical & Natural Sciences
    • Computer Science
    • Technical Reports from UMIACS
    • アイテム表示
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Learning to Detect Carried Objects with Minimal Supervision

    Thumbnail
    閲覧/開く
    CS-TR-5018.pdf (8.212Mb)
    No. of downloads: 858

    日付
    2012-12-21
    著者
    Dondera, Radu
    Morariu, Vlad I.
    Davis, Larry S.
    Metadata
    アイテムの詳細レコードを表示する
    抄録
    We propose a learning-based method for detecting carried objects that generates candidate image regions from protrusion, color contrast and occlusion boundary cues, and uses a classifier to filter out the regions unlikely to be carried objects. The method achieves higher accuracy than state of the art, which can only detect protrusions from the human shape, and the discriminative model it builds for the silhouette context-based region features generalizes well. To reduce annotation effort, we investigate training the model in a Multiple Instance Learning framework where the only available supervision is "walk" and "carry" labels associated with intervals of human tracks, i.e., the spatial extent of carried objects is not annotated. We present an extension to the miSVM algorithm that uses knowledge of the fraction of positive instances in positive bags and that scales to training sets of hundreds of thousands of instances.
    URI
    http://hdl.handle.net/1903/13339
    Collections
    • Technical Reports from UMIACS
    • Technical Reports of the Computer Science Department

    DRUM is brought to you by the University of Maryland Libraries
    University of Maryland, College Park, MD 20742-7011 (301)314-1328.
    Please send us your comments.
    Web Accessibility
     

     

    ブラウズ

    リポジトリ全体コミュニティ/コレクション公開日著者タイトル主題このコレクション公開日著者タイトル主題

    登録利用者

    ログイン登録
    Pages
    About DRUMAbout Download Statistics

    DRUM is brought to you by the University of Maryland Libraries
    University of Maryland, College Park, MD 20742-7011 (301)314-1328.
    Please send us your comments.
    Web Accessibility