Context models and out-of-context objects
Author(s)Choi, Myung Jin; Torralba, Antonio; Willsky, Alan S.
MetadataShow full item record
The context of an image encapsulates rich information about how natural scenes and objects are related to each other. Such contextual information has the potential to enable a coherent understanding of natural scenes and images. However, context models have been evaluated mostly based on the improvement of object recognition performance even though it is only one of many ways to exploit contextual information. In this paper, we present a new scene understanding problem for evaluating and applying context models. We are interested in finding scenes and objects that are “out-of-context”. Detecting “out-of-context” objects and scenes is challenging because context violations can be detected only if the relationships between objects are carefully and precisely modeled. To address this problem, we evaluate different sources of context information, and present a graphical model that combines these sources. We show that physical support relationships between objects can provide useful contextual information for both object recognition and out-of-context detection.
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Pattern Recognition Letters
Choi, Myung Jin, Antonio Torralba, and Alan S. Willsky. “Context Models and out-of-Context Objects.” Pattern Recognition Letters 33, no. 7 (May 2012): 853–62.
Author's final manuscript