Developing artificial intelligence systems that can interpret images

Today, Torralba is a tenured associate professor of electrical engineering and computer science at MIT, and an affiliate of the Computer Science and Artificial Intelligence Laboratory (CSAIL), where he develops AI systems that can interpret images to understand what scenes and objects they contain. I wanted to build systems that could put objects into context, to try to understand how different objects relate to each other, he says. So he began developing systems that used information gathered from the entire image to help identify individual objects. If an image contains an object perched on top of a table, for example, that object is unlikely to be anything very large, narrowing down considerably the number of things it could possibly be.

Author: Publication Date: Crawl Date: Source: Topic: Contributor: Type: Language: Format:
December 12, 2011 December 18, 2011 via Google News Applications MachineLearning Vision NewsFinder Text English HTML

Whitelist words:

  1. artifici intellig: 2 occurrences
  2. comput vision: 2 occurrences

Categorization (need >= 0.5 to match):

  1. AIOverview: 0.206832
  2. Agents: 0.0696414
  3. Applications: 0.816813
  4. CognitiveScience: 0.0833107
  5. Education: 0.002005
  6. Ethics: 0.0535493
  7. Games: 0.0319116
  8. History: 0.144755
  9. Interfaces: 0.00387358
  10. MachineLearning: 0.718211
  11. NaturalLanguage: 0.011404
  12. Philosophy: 0.00164604
  13. Reasoning: 0.0124522
  14. Representation: 0.00931135
  15. Robots: 0.00325437
  16. ScienceFiction: 0.0313643
  17. Speech: 0.0830703
  18. Systems: 0.0422432
  19. Vision: 1

Duplicates (threshold=0.17):


  1. Published
AAAI   Recent Changes   Edit   History   Print   Contact Us
Page last modified on December 19, 2011, at 12:00 AM