Knowledge Commons of Institute of Automation,CAS
Blended Grammar Network for Human Parsing | |
Xiaomei Zhang1,2![]() ![]() ![]() ![]() ![]() | |
2020 | |
会议名称 | European Conference on Computer Vision |
会议日期 | 2020 |
会议地点 | 线上会议 |
摘要 | Although human parsing has made great progress, it still faces a challenge, i.e., how to extract the whole foreground from similar or cluttered scenes effectively. In this paper, we propose a Blended Grammar Network (BGNet), to deal with the challenge. BGNet exploits the inherent hierarchical structure of a human body and the relationship of different human parts by means of grammar rules in both cascaded and paralleled manner. In this way, conspicuous parts, which are easily distinguished from the background, can amend the segmentation of inconspicuous ones, improving the foreground extraction. We also design a Part-aware Convolutional Recurrent Neural Network (PCRNN) to pass messages which are generated by grammar rules. To train PCRNNs effectively, we present a blended grammar loss to supervise the training of PCRNNs. We conduct extensive experiments to evaluate BGNet on PASCAL-Person-Part, LIP, and PPSS datasets. BGNet obtains state-of-the-art performance on these human parsing datasets. |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44896 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China 3.ObjectEye Inc., Beijing, China 4.NEXWISE Co., Ltd, Guangzhou, China |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Xiaomei Zhang,Yingying Chen,Bingke Zhu,et al. Blended Grammar Network for Human Parsing[C],2020. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ECCV_2020_Blended Gr(1602KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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