【外文文献速读】【图像处理】基于视频的行人属性识别
题目:
Video-Based Pedestrian Attribute Recognition
作者:
Zhiyuan Chen, Annan Li, Yunhong Wang
来源:
Computer Vision and Pattern Recognition (cs.CV)
(Submitted on 17 Jan 2019)
链接:
Video-Based Pedestrian Attribute Recognition
摘要
在本文中,我们首先通过基于视频的方法解决行人属性识别问题。挑战主要在于空间和时间建模以及如何将它们集成到有效和动态的行人表示中。为了解决这个问题,一个新的基于混合池策略的深度递归神经网络。由于公开可用的数据集很少,因此引入了一个新的用于行人属性识别的大型视频数据集,其中充分展示了基于视频的行人属性识别和提出的新网络架构的有效性。
英文原文
In this paper, we first tackle the problem of pedestrian attribute recognition by video-based approach.The challenge mainly lies in spatial and temporal modeling and how to integrating them for effective and dynamic pedestrian representation.To solve this problem, a novel deep recurrent neural network with hybrid pooling strategy is proposed.Since publicly available dataset is rare, a new large-scale video dataset for pedestrian attribute recognition is annotated, on which the effectiveness of both video-based pedestrian attribute recognition and the proposed new network architecture is well demonstrated.