Recurrent bag-of-features for visual information analysis
作者：
Highlights：
• Additional experiments were conducted with one state-of-the-art pooling method to further highlight the effectiveness of the ReBoF method.
• Additional experiments were conducted to evaluate the stability of the proposed method for different number of codewords.
• Conducted additional experiments to provide quantitative results of the proposed method (both for video and image applications).
• Additional figures were included to better explain how the proposed method works and how it can be applied on different scenarios.
摘要
•Additional experiments were conducted with one state-of-the-art pooling method to further highlight the effectiveness of the ReBoF method.•Additional experiments were conducted to evaluate the stability of the proposed method for different number of codewords.•Conducted additional experiments to provide quantitative results of the proposed method (both for video and image applications).•Additional figures were included to better explain how the proposed method works and how it can be applied on different scenarios.
论文关键词：Bag-of-Features,Recurrent neural networks,Pooling operators,Activity recognition
论文评审过程：Received 17 October 2019, Revised 2 April 2020, Accepted 14 April 2020, Available online 27 April 2020, Version of Record 11 May 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107380
