This is a past event. Its details are archived for historical purposes.
The contact information may no longer be valid.
Please visit our current events listings to look for similar events by title, location, or venue.
Friday, February 1, 2019 at 12:00pm to 1:30pm
Learning Machines Seminar Series
What: LMSS: Bill Freeman (Google and MIT)
When: Friday, Feb 1, 12:15 p.m. (pizza served at 12pm)
Where: Room 165, Bloomberg Center, Cornell Tech (map)
"Learning from Sight and Sound"
Vision and audition are rich channels through which to learn about the world. Taken together, they provide many opportunities for cross-modal learning. In the first half of the talk, I'll review my MIT lab's work in audio and visual research, showing some of the synergies possible. We ask, "what can you tell if you hit everything you see with a drumstick?" In the second half, I'll present "Looking to Listen", a research result from my team at Google. Given video filmed in a noisy environment, with potentially many speakers, we filter the noisy audio to play only the sound from a selected speaker. This may have applications in products that listen to people speaking, in video captioning, or in hearing aids.
William T. Freeman is the Thomas and Gerd Perkins Professor of Electrical Engineering and Computer Science at MIT, and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL) there. He was the Associate Department Head from 2011 - 2014. He is currently on a partial leave from MIT, managing a research group in Google in Cambridge, MA.
He received outstanding paper awards at computer vision or machine learning conferences in 1997, 2006, 2009 and 2012, and test-of-time awards for papers from 1990, 1995, and 2005. Previous research topics include steerable filters and pyramids, orientation histograms, the generic viewpoint assumption, color constancy, computer vision for computer games, and belief propagation in networks with loops.
He is active in the program or organizing committees of computer vision, graphics, and machine learning conferences. He was the program co-chair for ICCV 2005, and for CVPR 2013.