Department of Computer Science, 500 W. 120th St., New York, New York 10027 451
Computer Science Distinguished Lecture
Who: Bill Freeman, MIT, https://billf.mit.edu
When: Monday, December 2nd at 11:40am
Where: CSB 451
Vision and audition are rich perceptual channels and provide opportunities for cross- modal learning. To learn the visual appearance of different materials, we ask, "What can you tell if you hit everything you see with a drumstick?," joint work with Andrew Owens and others at MIT.
Freeman will also present "Looking to Listen," a search result from my team at Google. Given video filmed in a noisy environment, with multiple speakers, we filter the noisy audio to play only the sound from a selected speaker. This may have applications in closed captioning, assistive devices, and human-computer interaction.
Bill Freeman is the Thomas and Gerd Perkins Professor of Electrical Engineering and Computer Science at MIT, joining the faculty in 2001. His current research interests include motion re-rendering, computational photography, and learning for vision. Freeman received outstanding paper awards at computer vision or machine learning conferences in 1997, 2006, 2009 and 2012, and won "Test of Time" awards for papers written in 1990, 1995, and 2005. Previous research topics include steerable filters and pyramids, the generic viewpoint assumption, color constancy, bilinear models for separating style and content, and belief propagation in networks with loops. He holds over 30 patents.
Host: Carl Vondrick