Self-Attention based fine-grained cross-media hybrid network

作者：

Highlights：

• Propose a common attention space learning method for different feature spaces.

• Jointly learn the relative position encoding of local features and the spatial relationship between features.

• Achieve state-of-the-art performance on fine-grained cross-media retrieval task.

摘要

•Propose a common attention space learning method for different feature spaces.•Jointly learn the relative position encoding of local features and the spatial relationship between features.•Achieve state-of-the-art performance on fine-grained cross-media retrieval task.

论文关键词：Fine-Grained,Cross-Media,Retrieval,Attention

论文评审过程：Received 3 October 2021, Revised 20 April 2022, Accepted 24 April 2022, Available online 26 April 2022, Version of Record 22 May 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108748