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 2302.09018cs.CV
收藏

自监督动作表征学习:基于部分时空骨架序列

Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences

Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);The Chinese University of Hong Kong(香港中文大学);Shanghai AI Laboratory(上海人工智能实验室)

Yujie Zhou, Haodong Duan, Anyi Rao, Bing Su, Jiaqi Wang

AI总结:

提出部分时空学习框架,通过中心空间掩码和运动注意力时间掩码构建部分骨架序列,利用无负样本三元流结构学习局部关系,在多个数据集上达到SOTA并具鲁棒性。

摘要:

自监督学习在基于骨架的动作识别表征学习中展现了显著能力。现有方法主要侧重于应用全局数据增强来生成骨架序列的不同视图以进行对比学习。然而,由于骨架序列中丰富的动作线索,现有方法可能仅从全局视角学习区分不同骨架,而未充分利用不同骨架关节点与视频帧之间的局部关系,而这对于现实世界应用至关重要。在本工作中,我们提出了一种部分时空学习(PSTL)框架,通过一种独特的时空掩码策略构建的部分骨架序列来挖掘局部关系。具体而言,我们构建了一个无负样本的三元流结构,包括一个无任何掩码的锚定流、一个采用中心空间掩码(CSM)的空间掩码流,以及一个采用运动注意力时间掩码(MATM)的时间掩码流。分别测量锚定流与另外两个掩码流之间的特征互相关矩阵。(1)中心空间掩码从特征计算过程中丢弃选定的关节点,其中中心度较高的关节点被选中的可能性更大。(2)运动注意力时间掩码利用动作的运动信息,并以较高可能性移除运动较快的帧。我们的方法在NTU-60、NTU-120和PKU-MMD数据集上的多种下游任务中取得了最先进(SOTA)的性能。我们还进行了一项实际评估,在下游任务中部分骨架关节点丢失。与先前方法遭受较大性能下降不同,我们的PSTL仍能取得显著结果,验证了该方法的鲁棒性。代码:https://github.com/YujieOuO/PSTL.git。

英文摘要:

Self-supervised learning has demonstrated remarkable capability in representation learning for skeleton-based action recognition. Existing methods mainly focus on applying global data augmentation to generate different views of the skeleton sequence for contrastive learning. However, due to the rich action clues in the skeleton sequences, existing methods may only take a global perspective to learn to discriminate different skeletons without thoroughly leveraging the local relationship between different skeleton joints and video frames, which is essential for real-world applications. In this work, we propose a Partial Spatio-Temporal Learning (PSTL) framework to exploit the local relationship from a partial skeleton sequences built by a unique spatio-temporal masking strategy. Specifically, we construct a negative-sample-free triplet steam structure that is composed of an anchor stream without any masking, a spatial masking stream with Central Spatial Masking (CSM), and a temporal masking stream with Motion Attention Temporal Masking (MATM). The feature cross-correlation matrix is measured between the anchor stream and the other two masking streams, respectively. (1) Central Spatial Masking discards selected joints from the feature calculation process, where the joints with a higher degree of centrality have a higher possibility of being selected. (2) Motion Attention Temporal Masking leverages the motion of action and remove frames that move faster with a higher possibility. Our method achieves SOTA performance on NTU-60, NTU-120 and PKU-MMD under various downstream tasks. A practical evaluation is performed where some skeleton joints are lost in downstream tasks. In contrast to previous methods that suffer from large performance drops, our PSTL can still achieve remarkable results, validating the robustness of our method. Code: https://github.com/YujieOuO/PSTL.git.

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。

↑