Developing automated agents that intelligently perform complex real world tasks is time consuming and expensive. The most expensive part of developing these intelligent task perfo...
The paper describes a method for automatically extracting informative feature hierarchies for object classification, and shows the advantage of the features constructed hierarchic...
Recent work has shown the feasibility and promise of templateindependent Web data extraction. However, existing approaches use decoupled strategies ? attempting to do data record ...
Jun Zhu, Zaiqing Nie, Ji-Rong Wen, Bo Zhang, Wei-Y...
This paper describes a new method for the classification of a HTML document into a hierarchy of categories. The hierarchy of categories is involved in all phases of automated docum...
We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. When trained on natural images, the layers ...