have an interactive transcript feature enabled, which appears below the video when playing. Viewers can search for keywords in the video or click on any word in the transcript to jump to that point in the video. When searching, a dark bar with white vertical lines appears below the video frame. Each white line is an occurrence of the searched term and can be clicked on to jump to that spot in the video.
LEARNINGDeep Networks for Vision (1:14:06)
Date Posted:
July 5, 2017
Date Recorded:
August 26, 2016
CBMM Speaker(s):
Alan L. Yuille - Brains, Minds and Machines Summer Course 2016
Associated CBMM Pages:
Description:
Alan Yuille, Johns Hopkins University
Introduction to deep networks for visual tasks such as object detection and semantic segmentation; complex models that integrate deep networks with representations of parts and spatial relations, grammars, and top-down attention; and probing deep network internal representations of parts, visual concepts, and occlusions.