Webpage retrieval based on query by example for think tank construction

作者：

Highlights：

• A Query by Webpage model based on webpages’ visual and textual features is proposed.

• High-level visual features are extracted from snapshots via the proposed VEM module.

• Textual features from term and topic grain are considered for similarity estimation.

• A series of similarity metrics are proposed for webpage retrieval.

摘要

•A Query by Webpage model based on webpages’ visual and textual features is proposed.•High-level visual features are extracted from snapshots via the proposed VEM module.•Textual features from term and topic grain are considered for similarity estimation.•A series of similarity metrics are proposed for webpage retrieval.

论文关键词：Feature bootstrapping,Pre-trained neural networks,Query by example,Textual features,Visual features,Webpage retrieval

论文评审过程：Received 8 April 2021, Revised 15 September 2021, Accepted 15 September 2021, Available online 20 October 2021, Version of Record 20 October 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102767