Human-centric Scene Understanding for 3D Large-scale Scenarios
2023-10-06
会议录名称2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
ISSN1550-5499
页码20292-20302
发表状态已发表
DOI10.1109/ICCV51070.2023.01861
摘要

Human-centric scene understanding is significant for real-world applications, but it is extremely challenging due to the existence of diverse human poses and actions, complex human-environment interactions, severe occlusions in crowds, etc. In this paper, we present a large-scale multi-modal dataset for human-centric scene under-standing, dubbed HuCenLife, which is collected in diverse daily-life scenarios with rich and fine-grained annotations. Our HuCenLife can benefit many 3D perception tasks, such as segmentation, detection, action recognition, etc., and we also provide benchmarks for these tasks to facilitate related research. In addition, we design novel modules for LiDAR-based segmentation and action recognition, which are more applicable for large-scale human-centric scenarios and achieve state-of-the-art performance. The dataset and code can be found at https://github.com/4DVLab/HuCenLife.git. © 2023 IEEE.

关键词Computer vision Three-dimensional displays Codes Annotations Surveillance Benchmark testing Assistive robots
会议名称2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
会议地点Paris, France
会议日期1-6 Oct. 2023
URL查看原文
收录类别EI
语种英语
出版者Institute of Electrical and Electronics Engineers Inc.
EI入藏号20241215793203
原始文献类型Conference article (CA)
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/354923
专题信息科学与技术学院_硕士生
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_PI研究组_虞晶怡组
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_马月昕
共同第一作者Peishan Cong; Yichen Yao
作者单位
1.ShanghaiTech University
2.The University of Hong Kong
3.Shanghai AI Laboratory
4.The Chinese University of Hong Kong
第一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
Yiteng Xu,Peishan Cong,Yichen Yao,et al. Human-centric Scene Understanding for 3D Large-scale Scenarios[C]:Institute of Electrical and Electronics Engineers Inc.,2023:20292-20302.
条目包含的文件 下载所有文件
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
[Yiteng Xu]的文章
[Peishan Cong]的文章
[Yichen Yao]的文章
百度学术
百度学术中相似的文章
[Yiteng Xu]的文章
[Peishan Cong]的文章
[Yichen Yao]的文章
必应学术
必应学术中相似的文章
[Yiteng Xu]的文章
[Peishan Cong]的文章
[Yichen Yao]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 10.1109@ICCV51070.2023.01861.pdf
格式: Adobe PDF
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。