In this paper we propose a competition learning approach to coreference resolution. Traditionally, supervised machine learning approaches adopt the singlecandidate model. Neverthe...
Xiaofeng Yang, Guodong Zhou, Jian Su, Chew Lim Tan
In this paper we propose a novel algorithm for super resolution based on total variation prior and variational distribution approximations. We formulate the problem using a hierar...
S. Derin Babacan, Rafael Molina, Aggelos K. Katsag...
A main problem of data integration is the treatment of conflicts caused by different modeling of real-world entities, different data models or simply by different representations ...
We present a Resolution-Invariant Image Representation (RIIR) framework in this paper. The RIIR framework includes the methods of building a set of multi-resolution bases from tra...
In recent years a a number of psycholinguistic experiments have pointed to the interaction between language and vision. In particular, the interaction between visual attention and ...