Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/479314
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBabenko, Borisen_US
dc.contributor.authorMing-Hsuan Yangen_US
dc.contributor.authorBelongie, Sergeen_US
dc.date.accessioned2020-05-19T12:20:35Z-
dc.date.available2020-05-19T12:20:35Z-
dc.date.issued2011en_US
dc.identifier.other10.1109/TPAMI.2010.226en_US
dc.identifier.urihttp://localhost/handle/Hannan/284198en_US
dc.identifier.urihttp://localhost/handle/Hannan/479314-
dc.descriptionen_US
dc.descriptionen_US
dc.description.abstractIn this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called "tracking by detection" has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.en_US
dc.relation.haspartAL1935936.pdfen_US
dc.relation.urihttp://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5674053\npapers2://publication/doi/10.1109/TPAMI.2010.226\nhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5674053en_US
dc.subjectScience & Technologyen_US
dc.titleRobust Object Tracking with Online Multiple Instance Learningen_US
dc.typeArticleen_US
dc.typeArticleen_US
dc.journal.titleIEEE Transactions on Pattern Analysis and Machine Intelligenceen_US
Appears in Collections:2011

Files in This Item:
File SizeFormat 
AL1935936.pdf2.24 MBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBabenko, Borisen_US
dc.contributor.authorMing-Hsuan Yangen_US
dc.contributor.authorBelongie, Sergeen_US
dc.date.accessioned2020-05-19T12:20:35Z-
dc.date.available2020-05-19T12:20:35Z-
dc.date.issued2011en_US
dc.identifier.other10.1109/TPAMI.2010.226en_US
dc.identifier.urihttp://localhost/handle/Hannan/284198en_US
dc.identifier.urihttp://localhost/handle/Hannan/479314-
dc.descriptionen_US
dc.descriptionen_US
dc.description.abstractIn this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called "tracking by detection" has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.en_US
dc.relation.haspartAL1935936.pdfen_US
dc.relation.urihttp://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5674053\npapers2://publication/doi/10.1109/TPAMI.2010.226\nhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5674053en_US
dc.subjectScience & Technologyen_US
dc.titleRobust Object Tracking with Online Multiple Instance Learningen_US
dc.typeArticleen_US
dc.typeArticleen_US
dc.journal.titleIEEE Transactions on Pattern Analysis and Machine Intelligenceen_US
Appears in Collections:2011

Files in This Item:
File SizeFormat 
AL1935936.pdf2.24 MBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBabenko, Borisen_US
dc.contributor.authorMing-Hsuan Yangen_US
dc.contributor.authorBelongie, Sergeen_US
dc.date.accessioned2020-05-19T12:20:35Z-
dc.date.available2020-05-19T12:20:35Z-
dc.date.issued2011en_US
dc.identifier.other10.1109/TPAMI.2010.226en_US
dc.identifier.urihttp://localhost/handle/Hannan/284198en_US
dc.identifier.urihttp://localhost/handle/Hannan/479314-
dc.descriptionen_US
dc.descriptionen_US
dc.description.abstractIn this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called "tracking by detection" has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.en_US
dc.relation.haspartAL1935936.pdfen_US
dc.relation.urihttp://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5674053\npapers2://publication/doi/10.1109/TPAMI.2010.226\nhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5674053en_US
dc.subjectScience & Technologyen_US
dc.titleRobust Object Tracking with Online Multiple Instance Learningen_US
dc.typeArticleen_US
dc.typeArticleen_US
dc.journal.titleIEEE Transactions on Pattern Analysis and Machine Intelligenceen_US
Appears in Collections:2011

Files in This Item:
File SizeFormat 
AL1935936.pdf2.24 MBAdobe PDF