Jifeng Shen

Learn More
Sample misalignment exerts an important influence on training a rapid and accurate human detector, and it is a difficult problem to tackle with due to human articulation or manual annotation errors. Multiple instances learning method is an effective tool to deal with this difficulty without manual correction. In this paper, firstly, we propose a variable(More)
In the emerging cloud computing and services computing era, technology advancements enable the sharing of unlimited resources, the usage of services without ownership, and composition of services on demand. Besides these desired features of IT services provisioning, system reliability, data security, user's privacy are also highly concerned on the cloud.(More)