论文标题
骨骼的时间视角运输计划几次识别
Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition
论文作者
论文摘要
我们建议通过联合时间和摄像机观点对准（Jeanie）为基于3D骨架的动作识别提供一些射击学习管道。为了考虑3D主体接头的查询和支持序列之间的错位，我们提出了一个动态时间翘曲的高级变体，该变体在查询和支撑框架之间共同建模了每个平滑路径，以同时在有限的几个shot训练数据下同时实现临时和模拟相机视图空间中的最佳和模拟相机视图空间。基于简单的光谱图卷积（轻质线性图神经网络骨干线），用颞块编码器编码序列。我们还包括带有变压器的设置。最后，我们提出了一种基于相似性的损失，该损失鼓励同一类的序列对齐，同时防止不相关序列的比对。我们在NTU-60，NTU-1220，动力学 - 骨骼和UWA3D多维活动活动II上显示了最新的结果II。
We propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE). To factor out misalignment between query and support sequences of 3D body joints, we propose an advanced variant of Dynamic Time Warping which jointly models each smooth path between the query and support frames to achieve simultaneously the best alignment in the temporal and simulated camera viewpoint spaces for end-to-end learning under the limited few-shot training data. Sequences are encoded with a temporal block encoder based on Simple Spectral Graph Convolution, a lightweight linear Graph Neural Network backbone. We also include a setting with a transformer. Finally, we propose a similarity-based loss which encourages the alignment of sequences of the same class while preventing the alignment of unrelated sequences. We show state-of-the-art results on NTU-60, NTU-120, Kinetics-skeleton and UWA3D Multiview Activity II.
