Research Manager, Comcast Labs DC (2013 - now)

Since 2013, I manage the video content analysis group within Comcast Labs DC, but also expanded my focus to work on novel algorithms and product prototypes in the areas of personalized media recommendations, large-scale machine learning and big data analysis, specifically focusing on applications to combine video content analysis with big data within Comcast.

Lead Researcher, StreamSage/Comcast (2009 - 2013)

For the last couple years I have been working as a Lead Researcher as part of CoMPASS (Comcast Meta-data Products and Search Services, see this news article for some additional information) where I research novel audio/video information retrieval and content discovery technologies to help millions of households discover video and music content on their TV, PC, Phone, and Mobile devices.

Before that. I focused on computer vision and machine learning problems related to Search and Discovery of Multimedia Content in various domains such as news, sports, and entertainment. We specifically focussed on video summarization and chaptering, object and person recognition, and activity classification in premium broadcast video using multi-modal approaches that combined methods from video, speech, sound and natural language processing.

Siemens Corporate Research (2004 - 2008)

At Siemens I worked from August 2004 until December 2008 as a Research Scientist for the Real-time Vision and Modeling Department of Siemens Corporate Research (Princeton, NJ) and the Information & Communication Division of Siemens Corporate Technology (Munich, Germany). I mainly worked on pedestrian detection as part of a night vision system for cars (video of a comparison of our system against BMW and Daimler-Chrysler - in German) and for surveillance applications (see my CVPR 2007 paper).