Live and Learn: 基于增量视图的持续动作聚类
Live and Learn: Continual Action Clustering with Incremental Views
AI总结：
针对多视图动作聚类中视图增量获取及多视图不变信息学习难的问题，提出带类别记忆库和共识划分矩阵的持续动作聚类方法，经6个真实数据集验证，性能和时空效率优于15种现有基线方法。
摘要：
多视图动作聚类利用不同摄像机视图的互补信息提升聚类性能。尽管现有方法已取得显著进展，但它们假设所有摄像机视图均可提前获取，这在摄像机视图随时间增量增加的场景下并不现实。此外，学习多摄像机视图间的不变信息仍是一项具有挑战性的问题，尤其是在持续学习场景中。针对这些问题，我们提出了一种新颖的持续动作聚类（CAC）方法，该方法能够以持续学习的方式学习动作类别。具体而言，我们首先设计了一个类别记忆库，用于捕获并存储从历史视图中学到的类别。随后，当新的摄像机视图到来时，我们仅需维护一个共识划分矩阵，该矩阵可利用新到来的摄像机视图进行更新，而无需保留所有历史视图。最后，我们提出了一种三步交替优化方法，对类别记忆库和共识划分矩阵进行优化。在6个真实多视图动作数据集上的实验结果表明，与15种最先进的基线方法相比，CAC具有出色的聚类性能以及时间/空间效率。
英文摘要：
Multi-view action clustering leverages the complementary information from different camera views to enhance the clustering performance. Although existing approaches have achieved significant progress, they assume all camera views are available in advance, which is impractical when the camera view is incremental over time. Besides, learning the invariant information among multiple camera views is still a challenging issue, especially in continual learning scenario. Aiming at these problems, we propose a novel continual action clustering (CAC) method, which is capable of learning action categories in a continual learning manner. To be specific, we first devise a category memory library, which captures and stores the learned categories from historical views. Then, as a new camera view arrives, we only need to maintain a consensus partition matrix, which can be updated by leveraging the incoming new camera view rather than keeping all of them. Finally, a three-step alternate optimization is proposed, in which the category memory library and consensus partition matrix are optimized. The empirical experimental results on 6 realistic multi-view action collections demonstrate the excellent clustering performance and time/space efficiency of the CAC compared with 15 state-of-the-art baselines.
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。
