Stochastic Systems Group
Home Research Group Members Programs  
Demos Calendar Publications Mission Statement Alumni

SSG Seminar Abstract


Hierarchical Contextual Models for Object Categories

Myung Jin Choi
SSG, MIT


Context may play a crucial role in detecting and localizing multiple object categories in a cluterred scene. For example, a monitor, a keyboard, and a mouse co-occur often in an office scene, and they tend to appear at specific relative locations to one another. We propose a hierarchical tree model to encode contextual information: instead of capturing every pairwise relationship directly, we introduce hidden variables (e.g., desktop) as common factors for related objects (e.g., monitor, keyboard, mouse). A tree hierarchy can represent co-occurrences and spatial relationships among hundreds of object categories in a compact way. We show preliminary results of a tree learned from a set of labeled examples.

Joint work with Joseph Lim, Antonio Torralba, and Alan Willsky.



Problems with this site should be emailed to jonesb@mit.edu