Learning Category Correlations for Multi-label Image Recognition with Graph Networks

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.

Multi-Label Classification Word Embeddings

Multiple VLAD encoding of CNNs for image classification

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.

Classification General Classification +1

Diversified Visual Attention Networks for Fine-Grained Object 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.

Classification General Classification +1

A Study on Unsupervised Dictionary Learning and Feature Encoding for Action Classification

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.

Action Classification Dictionary Learning +2