Title: Precise quantification of natural behavior with computer vision Abstract: To understand the neural control of movement, cognition, and social interaction, we need to precisely quantify motor behaviors. Deep learning tools now enable to extract meaningful behavioral signals from raw videos, in high spatiotemporal resolution. These technologies are gaining increasing adoption in system neuroscience and…

Title: Multimodal Learning from Pixels to People Presenter: Carl Vondrick Abstract: People experience the world through modalities of sight, sound, words, touch, and more. By leveraging their natural relationships and developing multimodal learning methods, my research creates artificial perception systems with diverse skills, including spatial, physical, logical, and cognitive abilities, for flexibly analyzing visual data. This multimodal…