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.

提出了一种基于 JEANIE 的 3D 骨骼动作识别少样本学习方法，包括动态时间扭曲、简单光谱图卷积、线性图神经网络骨干和基于相似性的损耗函数，达到了在 NTU-60，NTU-120，运动学 - 骨骼和 UWA3D Multiview Activity II 数据集上的最先进的结果。

骨骼少样本动作识别的时空视角传输规划

Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition

In this paper, 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 demonstrate
state-of-the-art results on NTU-60, NTU-120, Kinetics-skeleton and UWA3D
Multiview Activity II.

本文提出了一种用于基于 3D 骨架的行为识别的 Few-shot Learning 流程，其中利用了 Dynamic Time Warping 方法，使用基于 Simple Spectral Graph Convolution 的时间块编码器进行序列编码，提出了一种基于相似性的损失函数，并在多个数据集上取得了最先进的结果。