Tuesday, 4 November 2014

Distinguished lecture series


Thursday, November 6, 2014
3:30 – 4:30 pm, DC 1302
Harry Shum

Since the launch of Bing (www.bing.com) in June 2009, we have seen Bing web search market share in the US more than doubled and Bing image search query share more than quadrupled. In this talk, I will share and discuss the challenges and opportunities in image understanding based on our experience building Bing image search. 

Specifically, I will talk about how we have significantly improved image search quality, and built differentiated image search user experience using NLP, entity, big data, machine learning and computer vision technologies. By leveraging big data from billions of search queries, billions of images on the web and from the social networks, and billions of user clicks, we have designed massive machine learning systems to continuously improve image search quality. With the focus on natural language and entity understanding, for instance, we have improved Bing’s ability to understand the user intent beyond queries and keywords. 

I will demonstrate with many examples how Bing has delivered a superior image search user experience,quantitatively, qualitatively and aesthetically, by utilizing computer vision techniques.

No comments:

Post a Comment