论文标题
统一少数和零射的自我识别
Unifying Few- and Zero-Shot Egocentric Action Recognition
论文作者
论文摘要
尽管在以自我为中心的行动识别方面进行了重大研究，但包括Epic-Kitchens在内的大多数方法和任务都假设一组固定的动作类别。固定集的分类对于基准测试方法很有用，但是由于动作的组成性，在实际设置中通常是不现实的，从而导致功能无限的心电图标签集。在这项工作中，我们通过统一两种流行的方法来探索一组开放式类别的概括：很少和零射门的概括（后者我们将其重新构建为跨模式的几个概括）。我们提出了一组来自Epic-Kitchens数据集的新拆分，允许评估开放式分类，并使用这些拆分表明，在常规的直接直接分类基线中添加度量学习损失可以提高零弹药的分类，而不是牺牲几个射击性能。
Although there has been significant research in egocentric action recognition, most methods and tasks, including EPIC-KITCHENS, suppose a fixed set of action classes. Fixed-set classification is useful for benchmarking methods, but is often unrealistic in practical settings due to the compositionality of actions, resulting in a functionally infinite-cardinality label set. In this work, we explore generalization with an open set of classes by unifying two popular approaches: few- and zero-shot generalization (the latter which we reframe as cross-modal few-shot generalization). We propose a new set of splits derived from the EPIC-KITCHENS dataset that allow evaluation of open-set classification, and use these splits to show that adding a metric-learning loss to the conventional direct-alignment baseline can improve zero-shot classification by as much as 10%, while not sacrificing few-shot performance.
