arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1703.07475cs.CV
收藏

PKU-MMD:一个大规模的连续多模态人类行为理解基准

PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding

Peking University(北京大学)

Chunhui Liu, Yueyu Hu, Yanghao Li, Sijie Song, Jiaying Liu

摘要:

尽管提出了许多3D人体活动基准,但大多数现有的动作数据集都集中在分割视频的动作识别任务上。缺乏标准的大规模基准测试,特别是对于当前流行的基于数据饥渴的深度学习方法。在本文中,我们介绍了一个新的大规模基准(PKU-MMD)的连续多模态三维人体动作的理解,并涵盖了广泛的复杂的人类活动,以及注释信息。PKU-MMD包含51个动作类别的1076个长视频序列,由66个主题在三个摄像机视图中执行。它包含近20,000个动作实例和总共540万帧。我们的数据集还提供多模态数据源,包括RGB,深度,红外辐射和骨架。使用不同的模式,我们在两种情况下对我们的数据集进行了广泛的实验,并通过各种指标评估不同的方法,包括新提出的评估协议2D-AP。我们相信这个大规模的数据集将有利于未来的研究行动检测的社区。

英文摘要:

Despite the fact that many 3D human activity benchmarks being proposed, most existing action datasets focus on the action recognition tasks for the segmented videos. There is a lack of standard large-scale benchmarks, especially for current popular data-hungry deep learning based methods. In this paper, we introduce a new large scale benchmark (PKU-MMD) for continuous multi-modality 3D human action understanding and cover a wide range of complex human activities with well annotated information. PKU-MMD contains 1076 long video sequences in 51 action categories, performed by 66 subjects in three camera views. It contains almost 20,000 action instances and 5.4 million frames in total. Our dataset also provides multi-modality data sources, including RGB, depth, Infrared Radiation and Skeleton. With different modalities, we conduct extensive experiments on our dataset in terms of two scenarios and evaluate different methods by various metrics, including a new proposed evaluation protocol 2D-AP. We believe this large-scale dataset will benefit future researches on action detection for the community.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑