Progressive Cognitive Human Parsing | |
Bingke Zhu1,2; Yingying Chen1,2; Ming Tang1,2; Jinqiao Wang1,2 | |
2018 | |
会议日期 | 2018.02 |
会议地点 | New Orleans, Louisiana, USA |
关键词 | Human Parsing Progressive Cognitive Networks |
DOI | 无 |
英文摘要 | Human parsing is an important task for human-centric understanding. Generally, two mainstreams are used to deal with this challenging and fundamental problem. The first one is employing extra human pose information to generate hierarchical parse graph to deal with human parsing task. Another one is training an end-to-end network with the semantic information in image level. In this paper, we develop an end-to-end progressive cognitive network to segment human parts. In order to establish a hierarchical relationship, a novel component-aware region convolution structure is proposed. With this structure, latter layers inherit prior component information from former layers and pay its attention to a finer component. In this way, we deal with human parsing as a progressive recognition task, that is, we first locate the whole human and then segment the hierarchical components gradually. The experiments indicate that our method has a better location capacity for the small objects and a better classification capacity for the large objects. Moreover, our framework can be embedded into any fully convolutional network to enhance the performance significantly. |
会议录出版者 | Sheila A. McIlraith,Kilian Q. Weinberger |
会议录出版地 | New Orleans, Louisiana, USA |
语种 | 英语 |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44999] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
作者单位 | 1.中国科学院大学 2.中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Bingke Zhu,Yingying Chen,Ming Tang,et al. Progressive Cognitive Human Parsing[C]. 见:. New Orleans, Louisiana, USA. 2018.02. |
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