Contextual and Bottom-Up Attention-Guided Large-Scale Visual Inferences

This course focuses on teaching learners how to make large-scale visual inferences using contextual and bottom-up attention guidance. The course covers topics such as neuroscience, unsupervised object discovery, computational neuroscience, multiple instance learning, gesture recognition, and classification. The teaching method involves a guest presentation by Dr. Zhuowen Tu. The course is designed for individuals interested in advanced visual inference techniques and computational neuroscience.