掩码运动预测器是强大的3D动作表征学习器
Masked Motion Predictors are Strong 3D Action Representation Learners
AI总结：
针对3D动作识别中监督数据不足的问题，提出MAMP自监督预训练框架，通过预测掩码关节的时序运动并以运动信息指导掩码，显著提升普通transformer并在多个基准上达到SOTA。
摘要：
在3D人体动作识别中，有限的监督数据使得充分挖掘transformer等强大网络的建模潜力变得具有挑战性。因此，研究人员一直在积极探索有效的自监督预训练策略。在本工作中，我们表明，与其遵循流行的预文本任务在人体关节中执行掩码自身成分重建，显式的上下文运动建模才是为3D动作识别学习有效特征表征成功的关键。形式上，我们提出了Masked Motion Prediction（MAMP，掩码运动预测）框架。具体而言，所提出的MAMP以掩码时空骨架序列作为输入，并预测被掩码人体关节对应的时序运动。考虑到骨架序列具有较高的时序冗余性，在我们的MAMP中，运动信息还充当经验性语义丰富度先验，用于指导掩码过程，从而促进模型更好地关注语义丰富的时序区域。在NTU-60、NTU-120和PKU-MMD数据集上的大量实验表明，所提出的MAMP预训练显著提升了所采用的普通transformer的性能，在没有额外花哨技巧的情况下取得了最先进结果。我们MAMP的源代码可在https://github.com/maoyunyao/MAMP获取。
英文摘要：
In 3D human action recognition, limited supervised data makes it challenging to fully tap into the modeling potential of powerful networks such as transformers. As a result, researchers have been actively investigating effective self-supervised pre-training strategies. In this work, we show that instead of following the prevalent pretext task to perform masked self-component reconstruction in human joints, explicit contextual motion modeling is key to the success of learning effective feature representation for 3D action recognition. Formally, we propose the Masked Motion Prediction (MAMP) framework. To be specific, the proposed MAMP takes as input the masked spatio-temporal skeleton sequence and predicts the corresponding temporal motion of the masked human joints. Considering the high temporal redundancy of the skeleton sequence, in our MAMP, the motion information also acts as an empirical semantic richness prior that guide the masking process, promoting better attention to semantically rich temporal regions. Extensive experiments on NTU-60, NTU-120, and PKU-MMD datasets show that the proposed MAMP pre-training substantially improves the performance of the adopted vanilla transformer, achieving state-of-the-art results without bells and whistles. The source code of our MAMP is available at https://github.com/maoyunyao/MAMP.
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。
