Modality-specific and shared generative adversarial network for cross-modal retrieval

作者：

Highlights：

• We propose a Modality-Specific and Shared Generative Adversarial Network approach.

• The modality-specific and modality-shared features are jointly explored and leveraged.

• The inter-modal invariance and the inter- and intra-modal discrimination is well modeled.

• Superiority of our approach is demonstrated on multiple benchmark multi-modal datasets.

摘要

•We propose a Modality-Specific and Shared Generative Adversarial Network approach.•The modality-specific and modality-shared features are jointly explored and leveraged.•The inter-modal invariance and the inter- and intra-modal discrimination is well modeled.•Superiority of our approach is demonstrated on multiple benchmark multi-modal datasets.

论文关键词：Cross-modal retrieval,Generative adversarial networks (GAN),Modality-specific feature learning,Modality-shared feature learning

论文评审过程：Received 10 June 2019, Revised 2 March 2020, Accepted 12 March 2020, Available online 14 March 2020, Version of Record 19 March 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107335