Fundamental Research Funds for the Central Universities [CCNU22XJ017]
机构署名:
本校为第一且通讯机构
摘要:
In recent years, Graph Convolutional Neural Networks (GCNs) have been widely used in tasks such as node semi-supervised classification, connection prediction and image clustering by constructing connection relations between nodes for information transfer of node features and achieving feature aggregation between nodes. To address the problem that the inter-relationship between image features is ignored in the task of educational object retrieval, the re-ranking task is transformed into the classification and ranking problem of educational object image nodes by utilizing graph convolutional neu...