Batch mode adaptive multiple instance learning for computer vision tasks
Multiple Instance Learning (MIL) has been widely exploited in many computer vision tasks, such as image retrieval, object tracking and so on. To handle ambiguity of instance labels in positive bags, the training process of traditional MIL methods is usually computationally expensive, which limits th...
Saved in:
Main Authors: | Li, Wen, Duan, Lixin, Tsang, Ivor Wai-Hung, Xu, Dong |
---|---|
其他作者: | School of Computer Engineering |
格式: | Conference or Workshop Item |
語言: | English |
出版: |
2013
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/98431 http://hdl.handle.net/10220/12473 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Domain adaptation from multiple sources : a domain-dependent regularization approach
由: Duan, Lixin, et al.
出版: (2013) -
Domain transfer multiple kernel learning
由: Duan, Lixin, et al.
出版: (2013) -
Co-labeling : a new multi-view learning approach for ambiguous problems
由: Duan, Lixin, et al.
出版: (2013) -
Visual event recognition in videos by learning from web data
由: Duan, Lixin, et al.
出版: (2013) -
Assessing the utility of synthetic images for computer vision tasks
由: Lim, Wei Chuan
出版: (2016)