In this work, we investigate how to automatically reassign the manually annotated labels at the image-level to those contextually derived semantic regions. First, we propose a bi-...
Xiaobai Liu, Bin Cheng, Shuicheng Yan, Jinhui Tang...
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
The last decade has witnessed the emergence of the Application Specific Instruction-set Processor (ASIP) as a viable platform for embedded systems. Extensible ASIPs allow the user...
: In this paper, we present a two-tiered scheduling approach for effective energy conservation in wireless sensor networks. The effectiveness of this mechanism relies on dynamicall...
For many users with a physical or motor disability, using a computer mouse or other pointing device to navigate the web is cumbersome or impossible due to problems with pointing a...
Leo Spalteholz, Kin Fun Li, Nigel Livingston, Foad...