J
Jian Sun
Researcher at Xi'an Jiaotong University
Publications - 394
Citations - 356427
Jian Sun is an academic researcher from Xi'an Jiaotong University. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 109, co-authored 360 publications receiving 239387 citations. Previous affiliations of Jian Sun include French Institute for Research in Computer Science and Automation & Tsinghua University.
Papers
More filters
Patent
Pop-up light field
TL;DR: In this article, a scene is split into one or more coherent layers and the boundaries of the coherent layers are propagated across a plurality of frames corresponding to the scene, and the splitting may be further refined to present a virtual view of the scene.
Posted Content
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
TL;DR: This work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs, and derives several practical guidelines for efficient network design, called ShuffleNet V2.
Journal ArticleDOI
EM algorithms for Gaussian mixtures with split-and-merge operation
TL;DR: A new modified EM algorithm is constructed that is efficient for unsupervised color image segmentation and developed through the singular value decomposition and the Cholesky decomposition.
Journal ArticleDOI
Topological methods for exploring low-density states in biomolecular folding pathways
Yuan Yao,Jian Sun,Xuhui Huang,Gregory R. Bowman,Gurjeet Singh,Michael Lesnick,Leonidas J. Guibas,Vijay S. Pande,Gunnar E. Carlsson +8 more
TL;DR: A computational approach to explore the relatively low populated transition or intermediate states in biomolecular folding pathways, based on a topological data analysis tool, MAPPER, with simulation data from large-scale distributed computing, inspired by classical Morse theory in mathematics.
Book ChapterDOI
Automatic exposure correction of consumer photographs
TL;DR: This paper will automate the interactive correction technique by estimating the image specific S-shaped non-linear tone curve that best fits the input image by creating a new Zone-based region-level optimal exposure evaluation, which would consider both the visibility of individual regions and relative contrast between regions.