In the near future, mobile devices are expected to have a storage capacity comparable to today's desktop machines. As the amount of infomation grows, conventional search tool...
We investigate the problem of learning document classifiers in a multilingual setting, from collections where labels are only partially available. We address this problem in the ...
Manifold reconstruction has been extensively studied for the last decade or so, especially in two and three dimensions. Recent advances in higher dimensions have led to new method...
Macro forest transducers (mfts) extend macro tree transducers (mtts) from ranked to unranked trees. Mfts are more powerful than mtts (operating on binary tree encodings) because t...
Conventional video summarization methods focus predominantly on summarizing videos along the time axis, such as building a movie trailer. The resulting video trailer tends to reta...