J
Jianqing Liang
Researcher at Shanxi University
Publications - 15
Citations - 162
Jianqing Liang is an academic researcher from Shanxi University. The author has contributed to research in topics: Computer science & Metric (mathematics). The author has an hindex of 5, co-authored 8 publications receiving 83 citations. Previous affiliations of Jianqing Liang include Tianjin University.
Papers
More filters
Journal ArticleDOI
Weighted Graph Embedding-Based Metric Learning for Kinship Verification
TL;DR: A novel weighted graph embedding-based metric learning (WGEML) framework for kinship verification based on the fact that family members usually show high similarity in facial features, despite their diversity is developed.
Journal ArticleDOI
Semisupervised Online Multikernel Similarity Learning for Image Retrieval
TL;DR: This work presents a new framework to exploit unlabeled images and develops a semisupervised OMKS algorithm, a multistage algorithm consisting of feature selection, selective ensemble learning, active sample selection, and triplet generation.
Journal ArticleDOI
Efficient multi-modal geometric mean metric learning
TL;DR: An effective and efficient metric learning algorithm for multi-modality data, i.e., Efficient Multi-modal Geometric Mean Metric Learning (EMGMML), which outperforms the state-of-the-art metric learning methods in terms of both accuracy and efficiency.
Journal ArticleDOI
Semi-supervised learning with mixed-order graph convolutional networks
TL;DR: A novel end-to-end ensemble framework, which is named mixed-order graph convolutional networks (MOGCN), which employs a novel ensemble module, in which the pseudo-labels of unlabeled nodes from various GCN learners are used to augment the diversity among the learners.
Journal ArticleDOI
Multi-view graph convolutional networks with attention mechanism
TL;DR: MAGCN as mentioned in this paper incorporates multiple views of topology and an attention-based feature aggregation strategy into the computation of graph convolution, which has good potential to produce a better learning representation for downstream tasks.