Feedback-based metric learning for activity recognition
作者：
Highlights：
• Incremental user activity recognition model learned from crowdsourcing user feedback.
• Similarity metric learning is introduced and improved the activity recognition model.
• Multi-metric learning mixed expert model integrated different user feedbacks.
• The mixture expert model interprets the process of user feedback generation.
• Manifested the efficiency by good accuracy between mixture expert and other methods.
摘要
•Incremental user activity recognition model learned from crowdsourcing user feedback.•Similarity metric learning is introduced and improved the activity recognition model.•Multi-metric learning mixed expert model integrated different user feedbacks.•The mixture expert model interprets the process of user feedback generation.•Manifested the efficiency by good accuracy between mixture expert and other methods.
论文关键词：Crowdsourcing,Activity recognition,Metric learning,MEMAR
论文评审过程：Received 13 April 2017, Revised 8 September 2018, Accepted 9 September 2018, Available online 10 September 2018, Version of Record 10 October 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.09.021
