C2C：面向零样本组合动作识别的组件到组合学习
C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition
AI总结：
提出零样本组合动作识别任务及基准Sth-com，并设计C2C方法（独立组件学习与组合推理模块）及增强训练策略，显著超越现有方法，达到新最优。
摘要：
组合动作由动态（动词）和静态（物体）概念组成。人类可以利用已学习的概念轻松识别未见过的组合。对于机器而言，解决此类问题需要模型能够识别由先前观察到的动词和物体组合而成的未见动作，因此需要所谓的组合泛化能力。为促进这一研究，我们提出了一个新的零样本组合动作识别（ZS-CAR）任务。为评估该任务，我们基于广泛使用的Something-Something V2数据集构建了一个新基准，即Something-composition（Sth-com）。我们还提出了一种新的组件到组合（C2C）学习方法来解决新的ZS-CAR任务。C2C包括一个独立的组件学习模块和一个组合推理模块。最后，我们设计了一种增强训练策略，以应对已见与未见组合之间组件变化的挑战，并处理学习已见与未见动作之间的微妙平衡。实验结果表明，所提出的框架显著超越了现有的组合泛化方法，并达到了新的最先进水平。新的Sth-com基准和代码可在https://github.com/RongchangLi/ZSCAR_C2C获取。
英文摘要：
Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can easily recognize unseen compositions using the learned concepts. For machines, solving such a problem requires a model to recognize unseen actions composed of previously observed verbs and objects, thus requiring so-called compositional generalization ability. To facilitate this research, we propose a novel Zero-Shot Compositional Action Recognition (ZS-CAR) task. For evaluating the task, we construct a new benchmark, Something-composition (Sth-com), based on the widely used Something-Something V2 dataset. We also propose a novel Component-to-Composition (C2C) learning method to solve the new ZS-CAR task. C2C includes an independent component learning module and a composition inference module. Last, we devise an enhanced training strategy to address the challenges of component variations between seen and unseen compositions and to handle the subtle balance between learning seen and unseen actions. The experimental results demonstrate that the proposed framework significantly surpasses the existing compositional generalization methods and sets a new state-of-the-art. The new Sth-com benchmark and code are available at https://github.com/RongchangLi/ZSCAR_C2C.
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。
