Cross-view Object Classification in Traffic Scene Surveillance Based on Transductive Transfer Learning | |
Yi Mo; Zhaoxiang Zhang; Yunhong Wang | |
2012-09-30 | |
会议名称 | International Conference on Image Processing |
会议录名称 | ICIP 2012 |
会议日期 | September 30 - October 3, 2012 |
会议地点 | Orlando, FL, USA |
摘要 | Object classification in traffic scene surveillance has been a hot topic in image processing field. A big challenge is that shooting view changes in different scenes, which leads to sharp accuracy decrease since training and test samples do not share the same distribution. Inductive transfer learning methods try to bridge this gap by making use of manually labeled target samples. However, it is in line with reality to conduct unsupervised transfer without manually labeling. In this paper, we propose an intuitive transductive transfer method by transferring instances across view. Experimental results indicate that our method outperforms traditional approaches such as inductive SVM and cluster method, and could even achieve a comparable performance compared with manually labeling approach. |
关键词 | Transductive Svm Traffic Scene Surveillance Object Classification Transfer Learning |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/13267 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Zhaoxiang Zhang |
推荐引用方式 GB/T 7714 | Yi Mo,Zhaoxiang Zhang,Yunhong Wang. Cross-view Object Classification in Traffic Scene Surveillance Based on Transductive Transfer Learning[C],2012. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论