no code implementations • 28 Sep 2019 • Qing Li, Xiaojiang Peng, Yu Qiao, Qiang Peng
In this paper, instead of using a pre-defined graph which is inflexible and may be sub-optimal for multi-label classification, we propose the A-GCN, which leverages the popular Graph Convolutional Networks with an Adaptive label correlation graph to model label dependencies.
no code implementations • 30 Jun 2017 • Qing Li, Qiang Peng, Chuan Yan
In this paper, we propose a special framework, which is the multiple VLAD encoding method with the CNNs features for image classification.
no code implementations • 28 Jun 2016 • Bo Zhao, Xiao Wu, Jiashi Feng, Qiang Peng, Shuicheng Yan
Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation.
no code implementations • 2 Sep 2013 • Xiaojiang Peng, Qiang Peng, Yu Qiao, Junzhou Chen, Mehtab Afzal
Many efforts have been devoted to develop alternative methods to traditional vector quantization in image domain such as sparse coding and soft-assignment.