Joint and individual matrix factorization hashing for large-scale cross-modal retrieval

作者：

Highlights：

• A joint and individual matrix factorization hashing method is proposed to simultaneously learn unified and individual hash codes for multimodal data.

• An effective optimization algorithm is put forward to solve the proposed method.

• Extensive experimental results on three multimodal data sets highlight the superiority of the proposed method over state-of-the-art unsupervised multimodal hashing methods.

摘要

•A joint and individual matrix factorization hashing method is proposed to simultaneously learn unified and individual hash codes for multimodal data.•An effective optimization algorithm is put forward to solve the proposed method.•Extensive experimental results on three multimodal data sets highlight the superiority of the proposed method over state-of-the-art unsupervised multimodal hashing methods.

论文关键词：Hashing,Multimodal,Retrieval,Cross-modal,Matrix factorization

论文评审过程：Received 3 November 2019, Revised 13 April 2020, Accepted 28 May 2020, Available online 31 May 2020, Version of Record 11 June 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107479