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
Poisson matting for images
TL;DR: In this article, a trimap for an image that specifies a background region, a foreground region, and an unknown region for the image wherein a boundary exists between the foreground region and the unknown region and wherein another boundary existed between the unknown regions and the background region is solved by solving a set of Poisson equations having boundary conditions for the two boundaries to provide a matte that distinguishes a foreground regions from a background regions in the unknown Region.
Proceedings ArticleDOI
A multi-sample, multi-tree approach to bag-of-words image representation for image retrieval
TL;DR: By encoding more information of the original image feature, this approach generates a much more discriminative visual word codebook that is also efficient in terms of both computation and space consumption, without losing the original repeatability of the visual features.
Proceedings ArticleDOI
Sparse-Coded Features for Image Retrieval.
Tiezheng Ge,Qifa Ke,Jian Sun +2 more
TL;DR: This paper illustrates that Fisher Vector, VLAD and BOF can be uniformly derived in two steps: i Encoding – separately map each local descriptor into a code, and ii Pooling – aggregate all codes from one image into a single vector.
Patent
Image semantic segmentation
Jifeng Dai,Kaiming He,Jian Sun +2 more
TL;DR: In this article, the semantic segmentation of the image is done by determining a semantic category for each pixel in the image at least in part based on the resulting segment features, which are extracted from the convolutional feature maps.
Proceedings ArticleDOI
NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
Goutam Bhat,Martin Danelljan,Radu Timofte,Kazutoshi Akita,Wooyeong Cho,Haoqiang Fan,Lanpeng Jia,Dae-Shik Kim,Bruno Lecouat,Youwei Li,Shuaicheng Liu,Ziluan Liu,Ziwei Luo,Takahiro Maeda,Julien Mairal,Christian Micheloni,Xuan Mo,Takeru Oba,Pavel Ostyakov,Jean Ponce,Sanghyeok Son,Jian Sun,Norimichi Ukita,Rao Muhammad,Umer Youliang Yan,Lei Yu,Magauiya Zhussip,Xueyi Zou +27 more
TL;DR: The NTIRE2021 challenge on burst super-resolution as mentioned in this paper was the first attempt to generate a clean RGB image with 4 times higher resolution given a RAW noisy burst as input.