MS2GAH: Multi-label semantic supervised graph attention hashing for robust cross-modal retrieval

作者：

Highlights：

• One of the first attempts of use GATs to solve cross-modal hashing issues.

• Pay more attention to the most important information to enhance the robustness.

• Design an label encoder to guide the feature extraction to narrow the modality gap.

• Use multi-label annotations to bridge the semantic relevance at a fine-grained level.

• MS2GAH can achieve satisfactory performance.

摘要

•One of the first attempts of use GATs to solve cross-modal hashing issues.•Pay more attention to the most important information to enhance the robustness.•Design an label encoder to guide the feature extraction to narrow the modality gap.•Use multi-label annotations to bridge the semantic relevance at a fine-grained level.•MS2GAH can achieve satisfactory performance.

论文关键词：Cross-modal retrieval,Deep hashing,Graph attention network

论文评审过程：Received 8 November 2021, Revised 1 March 2022, Accepted 30 March 2022, Available online 1 April 2022, Version of Record 11 April 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108676