B
Byung-soo Kim
Researcher at University of Michigan
Publications - 12
Citations - 444
Byung-soo Kim is an academic researcher from University of Michigan. The author has contributed to research in topics: Computer science & Support vector machine. The author has an hindex of 8, co-authored 10 publications receiving 403 citations.
Papers
More filters
Proceedings ArticleDOI
3D Scene Understanding by Voxel-CRF
TL;DR: A new method is proposed that allows us to jointly refine the 3D reconstruction of the scene (raw depth values) while accurately segmenting out the objects or scene elements from the3D reconstruction by introducing a new model which is called Voxel-CRF.
Proceedings Article
Comparing image classification methods: K-nearest-neighbor and support-vector-machines
TL;DR: A general Bag of Words model is used in order to compare two different classification methods, both K-Nearest-Neighbor and Support-Vector-Machine, and it is observed that the SVM classifier outperformed the KNN classifier.
Proceedings ArticleDOI
Accurate Localization of 3D Objects from RGB-D Data Using Segmentation Hypotheses
TL;DR: A novel framework is proposed that explores the compatibility between segmentation hypotheses of the object in the image and the corresponding 3D map using a generalization of the structural latent SVM formulation in 3D as well as the definition of a new loss function defined over the 3D space in training.
Journal ArticleDOI
Relating Things and Stuff via ObjectProperty Interactions
TL;DR: A framework for scene understanding that models both things and stuff using a common representation while preserving their distinct nature by using a property list is proposed, which allows us to enforce sophisticated geometric and semantic relationships between thing and stuff categories via property interactions in a single graphical model.
Book ChapterDOI
Relating things and stuff by high-order potential modeling
TL;DR: This paper proposes a framework for scene understanding that relates both things and stuff by using a novel way of modeling high order potentials and shows that an efficient graph-cut algorithm can be used to perform maximum a posteriori (MAP) inference in this model.