Bottom-Up Foreground-Aware Feature Fusion for Practical Person Search | |
Yang, Wenjie2,3,4; Huang, Houjing2,3,4; Chen, Xiaotang2,3,4; Huang, Kaiqi1,2,3,4 | |
刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY |
2021 | |
卷号 | 0期号:0页码:0 |
关键词 | Person Search, Person Re-Identification, Pedestrian Detection, Feature Learning, Attention |
英文摘要 | The key to efficient person search is jointly localizing pedestrians and learning discriminative representation for person re-identification (re-ID). Some recently developed models are built with separate detection and re-ID branches on top of shared region feature extraction networks. There are two factors that are detrimental to re-ID feature learning. One is the background information redundancy resulting from the large receptive field of neurons. The other is the body part missing and background clutter caused by inaccurate localization. In this work, a bottomup fusion (BUF) subnet is proposed to fuse the bounding box features pooled from multiple network stages. With a few parameters introduced, BUF leverages the multi-level features with various sizes of receptive fields to mitigate the backgroundbias problem. To further suppress the non-pedestrian regions, the newly introduced segmentation head generates a foreground probability map as guidance for the network to focus on the foreground regions. The resulting foreground attention module (FAM) enhances the foreground features. Moreover, for robust feature learning in practical person search, we propose to adaptively smooth the labels of the pedestrian boxes with consideration of the detection quality. Extensive experiments on PRW and CUHK-SYSU validate the effectiveness of the proposals. Our Bottom-Up Foreground-Aware Feature Fusion (BUFF) network with ALS achieves considerable gains over the state-of-the-art on PRW and competitive performance on CUHK-SYSU. |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44907] |
专题 | 智能系统与工程 |
通讯作者 | Huang, Kaiqi |
作者单位 | 1.CAS Center for Excellence in Brain Science and Intelligence Technology 2.Center for Research on Intelligent System and Engineering 3.University of Chinese Academy of Sciences 4.Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Yang, Wenjie,Huang, Houjing,Chen, Xiaotang,et al. Bottom-Up Foreground-Aware Feature Fusion for Practical Person Search[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2021,0(0):0. |
APA | Yang, Wenjie,Huang, Houjing,Chen, Xiaotang,&Huang, Kaiqi.(2021).Bottom-Up Foreground-Aware Feature Fusion for Practical Person Search.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,0(0),0. |
MLA | Yang, Wenjie,et al."Bottom-Up Foreground-Aware Feature Fusion for Practical Person Search".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 0.0(2021):0. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论