Powerful statistical models that can be learned efficiently from large amounts of data are currently revolutionizing computer vision. These models possess a rich internal structur...
The majority of the current information retrieval models weight the query concepts (e.g., terms or phrases) in an unsupervised manner, based solely on the collection statistics. I...
Fitting statistical 2D and 3D shape models to images is necessary for a variety of tasks, such as video editing and face recognition. Much progress has been made on local fitting...
Factoid questions often contain one or more assertions (facts) about their answers. However, existing question-answering (QA) systems have not investigated how the multiple facts ...
We present a general learning-based approach for phrase-level sentiment analysis that adopts an ordinal sentiment scale and is explicitly compositional in nature. Thus, we can mod...