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
Journal ArticleDOI
Guest Editorial: Deep Learning for Multimedia Computing
TL;DR: The twenty papers in this special section aim at providing a forum to present recent advancements in deep learning research that directly concerns the multimedia community.
Journal ArticleDOI
Breaking the Barrier to Transferring Link Information across Networks
TL;DR: This paper proposes the use of learning methods to perform link inference by transferring the link information from the source network to the target network by exploiting existing structures in source networks to rectify cross-network bias.
Journal ArticleDOI
Ontological Random Forests for Image Classification
TL;DR: The authors propose an ontological random forest algorithm where the of decision trees are determined by semantic relations among categories and hierarchical features are automatically learned by multiple-instance learning to capture visual dissimilarities at different concept levels.
Proceedings ArticleDOI
Integrated shadow mask for full angle deposition in fabrication of passive matrix OLED displays
Z.H. Huang,Guo-Jun Qi,X.T. Zeng +2 more
TL;DR: In this article, a novel structural design of an integrated shadow mask and its fabrication process that can be used for fabrication of passive matrix OLED displays is presented. But the mask structure is designed such that dead corner areas against various deposition angles are formed in between the humps and the side walls.
Posted Content
Rank Subspace Learning for Compact Hash Codes
TL;DR: This work proposes a novel hash learning framework that encodes feature's rank orders instead of numeric values in a number of optimal low-dimensional ranking subspaces and presents two versions of the algorithm: one with independent optimization of each hash bit and the other exploiting a sequential learning framework.