We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The appro...
As computer vision research considers more object categories and greater variation within object categories, it is clear that larger and more exhaustive datasets are necessary. How...
Brendan Collins, Jia Deng, Kai Li, Fei-Fei Li 0002
In the task of adaptive information filtering, a system receives a stream of documents but delivers only those that match a person's information need. As the system filters i...
Social tagging provides valuable and crucial information for large-scale web image retrieval. It is ontology-free and easy to obtain; however, irrelevant tags frequently appear, a...
Abstract. Learning ranking functions is crucial for solving many problems, ranging from document retrieval to building recommendation systems based on an individual user’s prefer...