ShanghaiTech University Knowledge Management System
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)
![]() |
ISSN | 1550-5499 |
卷号 | 2019-October |
页码 | 9468-9477 |
发表状态 | 已发表 |
DOI | 10.1109/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 |
修改评论
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。