Non-negative matrix completion for action detection
作者：
Highlights：
• Developing a multi-label classification framework with a convex optimization process for activity detection.
• Histogram correction for activity representation in each class, to localize activities in a weakly supervised setting.
• Proposing a new formulation for matrix completion to deal with classification/localization in video.
• Developing an activity recognition system in a totally weakly supervised multi-label setting.
• Developing a non-negative matrix completion framework based on Alternating Direction Method (ADM).
摘要
•Developing a multi-label classification framework with a convex optimization process for activity detection.•Histogram correction for activity representation in each class, to localize activities in a weakly supervised setting.•Proposing a new formulation for matrix completion to deal with classification/localization in video.•Developing an activity recognition system in a totally weakly supervised multi-label setting.•Developing a non-negative matrix completion framework based on Alternating Direction Method (ADM).
论文关键词：Matrix completion,Multi-label classification,Weakly supervised classification,Human activity recognition,Alternating direction method,Convex optimization
论文评审过程：Received 28 December 2012, Revised 16 February 2015, Accepted 23 April 2015, Available online 15 May 2015, Version of Record 4 June 2015.
论文官网地址：https://doi.org/10.1016/j.imavis.2015.04.006
