M
Ming Ye
Researcher at Microsoft
Publications - 19
Citations - 321
Ming Ye is an academic researcher from Microsoft. The author has contributed to research in topics: Optical flow & Global optimization. The author has an hindex of 12, co-authored 19 publications receiving 319 citations. Previous affiliations of Ming Ye include University of Washington.
Papers
More filters
Journal ArticleDOI
Estimating piecewise-smooth optical flow with global matching and graduated optimization
TL;DR: A global optimization formulation with three-frame matching and local variation is proposed and an efficient technique to minimize the resultant global energy is developed.
Proceedings ArticleDOI
Algorithm performance contest
Selim Aksoy,Ming Ye,M.L. Schauf,Mingzhou Song,Yalin Wang,Robert M. Haralick,J.M. Parker,J. Pivovarov,D. Royko,Changming Sun,Gunnar Farnebäck +10 more
TL;DR: This contest involved the running and evaluation of computer vision and pattern recognition techniques on different data sets with known groundwidth, including binary shape recognition, symbol recognition and image flow estimation.
Patent
Systems, methods, and computer-readable media for fast neighborhood determinations in dynamic environments
TL;DR: In this paper, the first vertex associated with a first ink stroke is defined, and the neighboring vertices are associated with ink stroke(s) other than the first stroke, where the ink stroke vertices having vertices that neighbor vertices included in the selection are defined.
Proceedings ArticleDOI
Optical flow from a least-trimmed squares based adaptive approach
Ming Ye,Robert M. Haralick +1 more
TL;DR: This adaptive two-stage robust scheme has significantly higher accuracy than non-robust algorithms and those only using robust methods at the OFC stage, and is illustrated on both synthetic and real data.
Patent
Parsing hierarchical lists and outlines
Ming Ye,Paul A. Viola +1 more
TL;DR: This paper used the Collins model for parsing non-textual information into hierarchical content, and assigned labels to lines that indicate how the lines relate to one another in a hierarchical content representation.