2017/09/28 by Xihui Liu, Liu, Xihui, Haiyu Zhao +13 · 90 citations
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolutional neural network #Deep learning #Discriminative model #Engineering #FOS: Computer and information sciences #Feature (linguistics) #Generality #Human Pose and Action Recognition #Key (lock) #Machine learning #Net (polyhedron) #Pattern recognition (psychology) #Pedestrian #Pedestrian detection #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.1709.09930
published in arXiv (Cornell University) (Cornell University) · Accepted by ICCV 2017
arxiv created 2017/09/28 · openalex publication_date 2017/09/28 · arxiv updated 2017/09/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.