期刊论文

Zeng, Jiangfeng(jfzeng@mail.ccnu.edu.cn)

英文

Computers & Electrical Engineering

0045-7906

2022

101

108002

10.1016/j.compeleceng.2022.108002

CRediT authorship contribution statement Yangtao Wang: Conceptualization, Methodology, Coding, Investigation, Formal analysis, Writing – original draft, Writing – review & editing. Yanzhao Xie: Data curation, Coding, Visualization, Writing – original draft. Jiangfeng Zeng: Conceptualization, acquisition, Resources, Supervision, Writing – review & editing, Visualization, Investigation. Hanpin Wang: Resources, Validation. Lisheng Fan: acquisition, Supervision, Writing – review & editing. Yufan Song: Investigation,

本校为其他机构

For multi-label image classification, existing studies either utilize a poor multi-step training workflow to explore the (local) relationships between the image target regions and their corresponding labels with attention mechanism or model the (global) label dependencies via graph convolution network (GCN) but fail to efficiently fuse these image features and label word vectors. To address these problems, we develop Cross-modal Fusion for Multi-label Image Classification with attention mechanism (termed as CFMIC), which combines attention mech...