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
Social media mining and knowledge discovery
TL;DR: This special issue includes five papers focusing on different aspects of social media mining and knowledge discovery, including a sparse semantic metric learning method that exploits heterogeneous information from the visual features and the tagging information of images, and formulates the learning problem as a sparse constrained one.
Proceedings ArticleDOI
Cross-VAE: Towards Disentangling Expression from Identity For Human Faces
TL;DR: This paper proposes to extend conditional VAE to a crossed version named Cross-VAE, which is able to use partially labeled data to disentangle expression from identity, and utilizes a symmetric training procedure where the output of each encoder is fed as the condition of the other.
Proceedings ArticleDOI
State-Driven Dynamic Sensor Selection and Prediction with State-Stacked Sparseness
TL;DR: A novel dynamic prediction model is developed that uses the notion of state-stacked sparseness to select a subset of the most critical sensors as a function of evolving system state.
Book ChapterDOI
Kernel-based linear neighborhood propagation for semantic video annotation
TL;DR: This approach combines the consistency assumption and the Local Linear Embedding (LLE) method in a nonlinear kernel-mapped space, which improves a recently proposed method Local Neighborhood Propagation (LNP) by tackling the limitation of its local linear assumption on the distribution of semantics.
Journal ArticleDOI
LEGO-MM : LE arning Structured Model by Probabilistic lo G ic O ntology Tree for M ulti M edia
TL;DR: A new framework is proposed, termed LEarning Structured Model by Probabilistic loGic Ontology Tree for MultiM edia (LEGO 1 -MM), which can seamlessly integrate both the new target training examples and the existing primitive concept models to infer the more complex concept models.