HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis

Xihui Liu, Haiyu Zhao, Maoqing Tian, Lu Sheng, Jing Shao, Shuai Yi, Junjie Yan, Xiaogang Wang; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 350-359

Abstract


Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an open problem. In this study, we propose a new attention-based deep neural network, named as HydraPlus-Net (HP-net), that multi-directionally feeds the multi-level attention maps to different feature layers. The attentive deep features learned from the proposed HP-net bring unique advantages: (1) the model is capable of capturing multiple attentions from low-level to semantic-level, and (2) it explores the multi-scale selectiveness of attentive features to enrich the final feature representations for a pedestrian image. We demonstrate the effectiveness and generality of the proposed HP-net for pedestrian analysis on two tasks, i.e. pedestrian attribute recognition and person re-identification. Intensive experimental results have been provided to prove that the HP-net outperforms the state-of-the-art methods on various datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Liu_2017_ICCV,
author = {Liu, Xihui and Zhao, Haiyu and Tian, Maoqing and Sheng, Lu and Shao, Jing and Yi, Shuai and Yan, Junjie and Wang, Xiaogang},
title = {HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}