Ethan Fetaya (Weizmann Institute of Science)
Tuesday, 24.1.2017, 11:30
I will present out approach to human pose estimation, where each location in the image votes for the position of each keypoint using a convolutional neural net. The voting scheme allows us to utilize information from the whole image, rather than rely on a sparse set of keypoint locations. Using dense, multi-target votes, not only produces good keypoint predictions, but also enables us to compute image-dependent joint keypoint probabilities by looking at consensus voting.
Joint work with Ita Lifshitz.
I received my PhD from the Weizmann Inst. under the supervision of Shimon Ullman and currently working at GM advanced technical institute in Israel.