Discover and Learn New Objects from Documentaries
Refereed conference paper presented and published in conference proceedings
已正式接受出版


全文

其它資訊
摘要Despite the remarkable progress in recent years, detect- ing objects in a new context remains a challenging task. Detectors learned from a public dataset can only work with a fixed list of categories, while training from scratch usually requires a large amount of training data with detailed annotations. This work aims to explore a novel approach – learning object detectors from documentary films in a weakly supervised manner. This is inspired by the observation that documentaries often provide dedicated exposition of certain object categories, where visual presentations are aligned with subtitles. We believe that object detectors can be learned from such a rich source of information. Towards this goal, we develop a joint probabilistic framework, where individual pieces of information, including video frames and subtitles, are brought together via both visual and linguistic links. On top of this formulation, we further derive a weakly supervised learning algorithm, where object model learning and training set mining are unified in an optimization procedure. Experimental results on a real world dataset demonstrate that this is an effective approach to learning new object detectors.
著者Kai Chen, Hang Song, Chen Change Loy, Dahua Lin
會議名稱IEEE Conference on Computer Vision and Pattern Recognition
會議開始日21.07.2017
會議完結日26.07.2017
會議地點Honolulu, Hawaii
會議國家/地區美國
出版年份2017
月份7
語言美式英語

上次更新時間 2018-20-01 於 18:58