Distinguished Lecture Series


"Probabilistic Models for Holistic Scene Understanding"

Daphne Koller, Stanford University

Wednesday, April 29, 2009, at 4:00 p.m.

Room 368 (CIT 3rd Floor)

Over recent years, computer vision has made great strides towards annotating parts of an image with coherent semantic labels (such as car, road, person, sky, and so on). However, current methods make no attempt to understand the image as a whole, and therefore cannot draw on powerful contextual cues to help resolve ambiguities. In this talk, I will describe some projects we have done that attempt to use probabilistic models to move us closer towards the goal.

The first part of the talk will present methods that use a more holistic scene analysis to improve our performance at core tasks such as object detection, segmentation, or 3D reconstruction. The second part of the talk will focus on finer-grained modeling of object shape, so as to allow us to annotate images with descriptive labels related to the object shape, pose, or activity (e.g., is a cheetah running or standing). These vision tasks rely on novel algorithms for core problems in machine learning and probabilistic models, such as efficient algorithms for probabilistic correspondence, transfer learning across related object classes for learning from sparse data, and more.

A reception will follow in the atrium.

Host: Eugene Charniak

To see the poster for this lecture, please click here.