We propose a semi-supervised model which segments and annotates images using very few labeled images and a large unaligned text corpus to relate image regions to text labels. Give...
Crowd-sourcing tools such as Mechanical Turk are popular for annotation of large scale image data sets. Typically, these annotations consist of bounding boxes or coarse outlines o...
Understanding intents from search queries can improve a user’s search experience and boost a site’s advertising profits. Query tagging via statistical sequential labeling mode...
Ye-Yi Wang, Raphael Hoffmann, Xiao Li, Jakub Szyma...
In this work, our objective is to heuristically discover a simplified form of functional dependencies between variables called weak dependencies. Once discovered, these relations...
We present a novel algorithm (which we call "FragTrack") for tracking an object in a video sequence. The template object is represented by multiple image fragments or pa...