arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.00394cs.CV
收藏

IKEA ASM 数据集:通过动作、物体和姿态理解人们组装家具

The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose

Australian National University(澳大利亚国立大学);Australian Centre for Robotic Vision (ACRV)(澳大利亚机器人视觉中心);University of Technology Sydney(悉尼科技大学)

Yizhak Ben-Shabat, Xin Yu, Fatemeh Sadat Saleh, Dylan Campbell, Cristian Rodriguez-Opazo, Hongdong Li, Stephen Gould

AI总结:

为解决现有数据集在视角和标注上的局限,本文提出了包含三百万帧、多视角的家具组装视频数据集 IKEA ASM,涵盖深度、原子动作、物体分割和人体姿态,并对其动作识别等任务进行了基准测试,以推动多模态整体性方法的发展。

摘要:

大型标注数据集的可用性是应用深度学习方法解决各种计算机视觉任务的关键要求。在理解人类活动的背景下,现有的公开数据集虽然规模庞大,但通常局限于单一 RGB 摄像头,且仅提供逐帧或逐片段的动作标注。为了实现对人类活动更丰富的分析与理解,我们引入了 IKEA ASM——这是一个包含三百万帧、多视角的家具组装视频数据集,其中包含深度信息、原子动作、物体分割以及人体姿态。此外,我们在这个具有挑战性的数据集上对视频动作识别、物体分割和人体姿态估计任务的知名方法进行了基准测试。该数据集有助于开发整体性方法,通过整合多模态和多视角数据以在这些任务上取得更佳表现。

英文摘要:

The availability of a large labeled dataset is a key requirement for applying deep learning methods to solve various computer vision tasks. In the context of understanding human activities, existing public datasets, while large in size, are often limited to a single RGB camera and provide only per-frame or per-clip action annotations. To enable richer analysis and understanding of human activities, we introduce IKEA ASM -- a three million frame, multi-view, furniture assembly video dataset that includes depth, atomic actions, object segmentation, and human pose. Additionally, we benchmark prominent methods for video action recognition, object segmentation and human pose estimation tasks on this challenging dataset. The dataset enables the development of holistic methods, which integrate multi-modal and multi-view data to better perform on these tasks.

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。

↑