Search
Now showing items 1-3 of 3
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 ...
Single-Shot Object Detection with Enriched Semantics
(Center for Brains, Minds and Machines (CBMM), 2018-06-19)
We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic ...
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 ...