Data-level information enhancement: Motion-patch-based Siamese Convolutional Neural Networks for human activity recognition in videos
作者：
Highlights：
• Minimize the problem of bad samples generation caused due to random cropping.
• A new attempt to improve results by data-level motion information enhancement.
• A simple but effective method to extract saliency motion regions in video clips.
• An end-to-end learning frame work without training hand-crafted features.
• The proposed method improved the performance upon state-of-the-art approaches.
摘要
•Minimize the problem of bad samples generation caused due to random cropping.•A new attempt to improve results by data-level motion information enhancement.•A simple but effective method to extract saliency motion regions in video clips.•An end-to-end learning frame work without training hand-crafted features.•The proposed method improved the performance upon state-of-the-art approaches.
论文关键词：Human activity recognition,Data augmentation,Deep learning,3D Convolutional Neural Networks
论文评审过程：Received 17 July 2019, Revised 11 January 2020, Accepted 13 January 2020, Available online 14 January 2020, Version of Record 20 January 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113203
