— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
We present an efficient system for video search that maximizes the use of human bandwidth, while at the same time exploiting the machine’s ability to learn in real-time from use...
Alexander G. Hauptmann, Wei-Hao Lin, Rong Yan, Jun...
Schema Matching is the problem of identifying corresponding elements in different schemas. Discovering these correspondences or matches is inherently difficult to automate. Past s...
Jayant Madhavan, Philip A. Bernstein, AnHai Doan, ...
Many applications in text and speech processing require the analysis of distributions of variable-length sequences. We recently introduced a general kernel framework, rational ker...
Heuristic measures for estimating the quality of attributes mostly assume the independence of attributes so in domains with strong dependencies between attributes their performanc...