Pose-Aware Multi-Level Feature Network for Human Object Interaction Detection
2019-10
会议录名称2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
ISSN1550-5499
卷号2019-October
页码9468-9477
发表状态已发表
DOI10.1109/ICCV.2019.00956
摘要

Reasoning human object interactions is a core problem in human-centric scene understanding and detecting such relations poses a unique challenge to vision systems due to large variations in human-object configurations, multiple co-occurring relation instances and subtle visual difference between relation categories. To address those challenges, we propose a multi-level relation detection strategy that utilizes human pose cues to capture global spatial configurations of relations and as an attention mechanism to dynamically zoom into relevant regions at human part level. We develop a multi-branch deep network to learn a pose-augmented relation representation at three semantic levels, incorporating interaction context, object features and detailed semantic part cues. As a result, our approach is capable of generating robust predictions on fine-grained human object interactions with interpretable outputs. Extensive experimental evaluations on public benchmarks show that our model outperforms prior methods by a considerable margin, demonstrating its efficacy in handling complex scenes.

关键词Proposals Visualization Feature extraction Cognition Task analysis Semantics Neural networks
会议地点Seoul, Korea (South)
会议日期27 Oct.-2 Nov. 2019
URL查看原文
收录类别EI ; CPCI-S ; CPCI
资助项目National Natural Science Foundation of China[61703195] ; [18ZR1425100]
出版者Institute of Electrical and Electronics Engineers Inc.
EI入藏号20201208326890
EI主题词Object detection ; Semantics
EI分类号Data Processing and Image Processing:723.2 ; Computer Applications:723.5
原始文献类型Conferences
来源库IEEE
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/104310
专题信息科学与技术学院_博士生
信息科学与技术学院_PI研究组_何旭明组
信息科学与技术学院_硕士生
通讯作者Wan, Bo
作者单位
ShanghaiTech University, Shanghai, China
第一作者单位上海科技大学
通讯作者单位上海科技大学
第一作者的第一单位上海科技大学
推荐引用方式
GB/T 7714
Wan, Bo,Zhou, Desen,Liu, Yongfei,et al. Pose-Aware Multi-Level Feature Network for Human Object Interaction Detection[C]:Institute of Electrical and Electronics Engineers Inc.,2019:9468-9477.
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
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Wan, Bo]的文章
[Zhou, Desen]的文章
[Liu, Yongfei]的文章
百度学术
百度学术中相似的文章
[Wan, Bo]的文章
[Zhou, Desen]的文章
[Liu, Yongfei]的文章
必应学术
必应学术中相似的文章
[Wan, Bo]的文章
[Zhou, Desen]的文章
[Liu, Yongfei]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。