We present an interactive application that enables users to improve the visual aesthetics of their digital photographs using spatial recomposition. Unlike earlier work that focuse...
The problem of multimodal data mining in a multimedia database can be addressed as a structured prediction problem where we learn the mapping from an input to the structured and i...
Zhen Guo, Zhongfei Zhang, Eric P. Xing, Christos F...
In this paper, we propose a new comprehensive methodology in order to evaluate the performance of noisy historical document recognition techniques. We aim to evaluate not only the...
Spatiotemporal data is associated with vast amounts of raw samples. Given the limited computational resources typically available, an initial organization of this data supporting
...
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...