Search
Now showing items 1-2 of 2
DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion
(Center for Brains, Minds and Machines (CBMM), 2018-06-19)
In this paper, we study the task of detecting semantic parts of an object, e.g., a wheel of a car, under partial occlusion. We propose that all models should be trained without seeing occlusions while being able to transfer ...
Visual concepts and compositional voting
(Center for Brains, Minds and Machines (CBMM), 2018-03-27)
It is very attractive to formulate vision in terms of pattern theory [26], where patterns are defined hierarchically by compositions of elementary building blocks. But applying pattern theory to real world images is very ...