基于凸包自适应平移的骨架动作识别去偏方法
De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift
AI总结：
针对骨架动作识别中因世界坐标系原点选择导致的实体偏差问题，提出基于凸包自适应平移的归一化方法CHASE，通过参数化网络和辅助目标减少偏差，在7个数据集上显著提升多种骨干网络的识别性能。
AI中文摘要：
骨架序列能够表示个体动作以及多实体交互，涵盖人体、手部、物体和机器人。现有的骨架动作与交互识别方法通常采用晚期融合策略，该策略假设个体是独立同分布的，以训练一个权重共享的实体编码器。然而，在各种骨架数据中观察到的实体偏差违反了这一假设，导致骨干模型的优化欠佳，可能产生错误的识别结果。这种偏差源于世界坐标系的初始配置，其中原点的选择常常在表示中引入偏差。为此，我们提出一种基于凸包自适应平移的归一化方法来减少实体偏差（CHASE），以提升多种骨架动作与交互识别任务的性能。为了自适应地对输入骨架施加合理的平移，我们构建了一个即插即用的参数化网络，确保重定位后的世界原点位于骨架凸包内部，从而通过限制搜索空间避免不收敛问题。为了进一步最小化实体偏差，我们引入了一个辅助目标，利用成对分布距离来指导网络优化。为了支持单实体和多实体动作，我们提出了一种子实体策略，为这两种场景提供一致的公式化表述。此外，CHASE展示了与各种骨架内模态（如骨骼和速度）的兼容性，突显了其适应性。本质上，我们的方法作为一种减少实体偏差的归一化方法，使后续分类器能够在不同设置下获得改进的识别性能。在7个数据集上的大量实验验证了我们的方法，能够无缝集成到各种骨干网络中并显著提升其性能。
英文摘要：
Skeleton sequences can represent both individual actions and multi-entity interactions, encompassing human bodies, hands, objects, and robots. Existing approaches to recognize skeleton-based actions and interactions usually adopt a late fusion strategy, which expects individuals are independent and identically distributed to train a robust weight-shared entity encoder. However, observed entity bias in various skeletal data violates this assumption, leading to suboptimal optimization of backbone models that might produce wrong recognition results. This bias arises from the world coordinate system's initial configuration, where the choice of origin often creates bias in representation. To this end, we propose a Convex Hull Adaptive Shift based normalization method to reduce Entity bias (CHASE), improving performance across a variety of skeleton-based action and interaction recognition tasks. To adaptively apply plausible shifts to the input skeletons, we formulate a plug-and-play parameterized network that ensures the relocated world origin lies within the skeleton convex hull, which avoids non-convergence by limiting the search space. To further minimize entity bias, we incorporate an auxiliary objective that leverages pair-wise distribution distances to guide network optimization. To support both single- and multi-entity actions, we propose a sub-entity strategy that offers a consistent formulation for both scenarios. Moreover, CHASE demonstrates compatibility with various intra-skeleton modalities, such as bones and velocities, highlighting its adaptability. Essentially, our method works as a normalization approach to reduce entity bias, enabling subsequent classifiers to achieve improved recognition performance across diverse settings. Extensive experiments on 7 datasets verify our approach by seamlessly integrating with various backbones and significantly boosting their performance.
