LarryDavis2011

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Invited talk by Larry S. Davis

Davis.jpg

Larry S. Davis
Chair of the Department of Computer Science
Professor in the Institute for Advanced Computer Studies and the Department of Computer Science
University of Maryland

  • Date: Tuesday, 29 November 2011
  • Time: 4.00pm
  • Location: MI 00.12.019

Context in image (and video) understanding

Abstract:

In spite of the significant effort that has been devoted to the core problems of object and action recognition in images and videos, the recognition performance of state of the art algorithms is well below what would be required for any successful deployment in many applications. Additionally, there are challenging combinatorial problems associated with constructing globally “optimal” descriptions of images and videos in terms of potentially very large collections of object and action models. The constraints that are utilized in these optimization procedures are loosely referred to as “context.” So, for example, vehicles are generally supported by the ground, so that an estimate of ground plane location parameters in an image constrains positions and apparent sizes of vehicles. Another source of context are the everyday spatial and temporal relationships between objects and actions; so, for example, keyboards are typically “on” tables and not “on” cats. The first part of the talk will discuss how visually grounded models of object appearance and relations between objects can be simultaneously learned from weakly labeled images (images which are linguistically but not spatially annotated – i.e., we are told there is a car in the image, but not where the car is located). Next, I will discuss how these models can be more efficiently learned using active learning methods. Once these models are acquired, one approach to inferring what objects appear in a new image is to segment the image into pieces, construct a graph based on the regions in the segmentation and the relationships modeled, and then apply probabilistic inference to the graph. However, this typically results in a very dense graph with many “noisy” edges, leading to inefficient and inaccurate inference. I will briefly describe a learning approach that can construct smaller and more informative graphs for inference. Finally, I will relax the (unreasonable) assumption that one can segment an image into regions that correspond to objects, and describe an approach that can simultaneously construct instances of objects out of collections of connected segments that look like objects, while also softly enforcing contextual constraints.

WebEventForm
Title: Context in image (and video) understanding
Date: 29 November 2011
Location: MI 00.12.019
Abstract: We are honored to have Prof. Larry Davis visiting the computer science department and giving a Fachkolloquium on “Context in image (and video) understanding”.
Imageurl: Davis.jpg
Type: News
Videourl:  
Conferencelink:  


Edit | Attach | Refresh | Diffs | More | Revision r1.2 - 25 Nov 2011 - 20:23 - NassirNavab

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif