G
Guo-Jun Qi
Researcher at Huawei
Publications - 263
Citations - 12701
Guo-Jun Qi is an academic researcher from Huawei. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 53, co-authored 248 publications receiving 9928 citations. Previous affiliations of Guo-Jun Qi include China University of Science and Technology & University of Science and Technology of China.
Papers
More filters
Posted Content
GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations
Xiang Gao,Wei Hu,Guo-Jun Qi +2 more
TL;DR: GraphTER as discussed by the authors proposes an unsupervised learning of graph Transformation Equivariant Representations (GraphTER), which allows to sample different groups of nodes from a graph and then transform them node-wise isotropically or anisotropically.
Journal ArticleDOI
Field aided lateral crystallization of amorphous silicon with large grain formation
TL;DR: In this paper, a field aided lateral crystallization of amorphous silicon has been carried out at 500 °C with an electric field of 200 V/cm, where large crystalline silicon grains with sizes over 100 μm have been formed in the laterally crystallized region.
BookDOI
MultiMedia modeling: 22nd International conference, MMM 2016 Miami, FL, USA, january 4–6, 2016 proceedings, part II
TL;DR: The two-volume set LNCS 9516 and 9517 constitutes the thoroughly refereed proceedings of the 22nd International Conference on Multimedia Modeling, MMM 2016, held in Miami, FL, USA, in January 2016.
Proceedings Article
PhotoNet: A similarity-aware image delivery service for situation awareness
TL;DR: It is shown that, in resource constrained networks, reducing semantic redundancy can significantly improve utility, and is evaluated in an emulated disaster recovery scenario, with a predetermined set of problem locales that need attention.
Journal ArticleDOI
CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution
TL;DR: This work proposes an efficient CNN-Transformer Cooperation Network (CTCNet) for face super-resolution tasks, which uses the multi-scale connected encoder-decoder architecture as the backbone and can outperform other state-of-the-art methods signi ficantly.