A Multi-Feature Part-Based Object Detection System
- -
Google Tech Talks May 25, 2007 ABSTRACT I will start with an overview on object recognition systems which use local features and analyze their strengths and weaknesses. I will then present a general purpose part-based object detection system which we evaluated on a benchmark pedestrian detection data set . In a first step, the system computes ... Read more
0 people like this
- -: A Multi-Feature Part-Based Object Detection System
October 9, 2007 (over 16 years ago)Google Tech Talks May 25, 2007 ABSTRACT I will start with an overview on object recognition systems which use local features and analyze their strengths and weaknesses. I will then present a general purpose part-based object detection system which we evaluated on a benchmark pedestrian detectio...
0 people like this
- -: Learning Object Appearance Models via Transformed...
October 9, 2007 (over 16 years ago)Google Tech Talks March 6, 2007 ABSTRACT Object recognition systems use features extracted from images to localize and categorize objects. Such methods must be robust to the rich variability of natural scenes, and the often small size of training databases. In this talk, we describe hierarchica...
0 people like this
- -: From Desktops to Donuts: Object-Caps Across Scales
October 9, 2007 (over 16 years ago)Google TechTalks July 26, 2006 Marc Stiegler Visiting Scholar Hewlett-Packard Laboratories Mr. Stiegler is the developer of CapDesk, a graphical desktop system invulnerable to traditional computer viruses that first explored the secure cooperation concepts now being used by the Polaris secure d...
0 people like this
- -: The Lazy Programmer's Guide to Secure Computing
March 19, 2010 (about 14 years ago)Google Tech Talk March 11, 2010 ABSTRACT Presented by Marc Stiegler. This presentation starts with a simple block of code written by the Lazy Programmer, to observe how laziness made the code more compact and simpler. We then define the Principle of Least Authority(POLA), and explain why it is...
0 people like this(4 results)