Reconstruction-based supervised hashing
作者：
Highlights：
• We propose a reconstruction-based supervised hashing (RSH) method to learn compact binary codes with holistic structure preservation. The proposed method characterizes the similarity structure by the relationship between each data point and the structure generated by the remaining points.
• We extend our RSH method to cross-modal data by distilling the semantic reconstruction-based correlation and learning the common representations simultaneously, which characterizes the semantic correlation by the relationship between data points and structures in the common hamming space.
• Experimental results in both single-modal and cross-modal datasets demonstrate the effectiveness of our methods when compared to several recently proposed approaches.
摘要
•We propose a reconstruction-based supervised hashing (RSH) method to learn compact binary codes with holistic structure preservation. The proposed method characterizes the similarity structure by the relationship between each data point and the structure generated by the remaining points.•We extend our RSH method to cross-modal data by distilling the semantic reconstruction-based correlation and learning the common representations simultaneously, which characterizes the semantic correlation by the relationship between data points and structures in the common hamming space.•Experimental results in both single-modal and cross-modal datasets demonstrate the effectiveness of our methods when compared to several recently proposed approaches.
论文关键词：
论文评审过程：Received 1 September 2017, Revised 29 January 2018, Accepted 2 February 2018, Available online 6 February 2018, Version of Record 23 February 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.02.003
