Directly solving normalized cut for multi-view data
作者：
Highlights：
• The new method learns a set of implicit weights for each view to identify its quality, and the view weights can be adjusted by an additional parameter for better results.
• A parameter p is introduced to adjust the distribution of these view weights to obtain better results.
• An iterative algorithm with linear time complexity is proposed to directly optimize the new model without eigen-decomposition and post-processing.
摘要
•The new method learns a set of implicit weights for each view to identify its quality, and the view weights can be adjusted by an additional parameter for better results.•A parameter p is introduced to adjust the distribution of these view weights to obtain better results.•An iterative algorithm with linear time complexity is proposed to directly optimize the new model without eigen-decomposition and post-processing.
论文关键词：Clustering,Graph cut,Multi-view
论文评审过程：Received 7 December 2020, Revised 7 May 2022, Accepted 20 May 2022, Available online 22 May 2022, Version of Record 27 May 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108809
