GaitNet: An end-to-end network for gait based human identification
作者：
Highlights：
• We are the first to model human silhouette extraction and gait recognition in one framework in a unified end-to-end learning manner.
• We find that joint learning can lead to obvious performance enhancement over separate learning.
• We explore to add siamese loss for metric learning across the segmentation network and recognition network.
• We build a new outdoor gait database containing three challenging scenes.
• We provide extensive empirical evaluations in experiments and obtain the state-of-the-art results on three gait recognition datasets.
摘要
•We are the first to model human silhouette extraction and gait recognition in one framework in a unified end-to-end learning manner.•We find that joint learning can lead to obvious performance enhancement over separate learning.•We explore to add siamese loss for metric learning across the segmentation network and recognition network.•We build a new outdoor gait database containing three challenging scenes.•We provide extensive empirical evaluations in experiments and obtain the state-of-the-art results on three gait recognition datasets.
论文关键词：Gait recognition,Video-based human identification,End-to-end CNN,Joint learning
论文评审过程：Received 17 September 2018, Revised 17 July 2019, Accepted 31 July 2019, Available online 31 July 2019, Version of Record 6 August 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.106988
