Abstract
Point-level weakly-supervised temporal action localization (PWTAL) aims to localize actions with only a single timestamp annotation for each action instance. Existing methods tend to mine dense pseudo labels to alleviate the label sparsity, but overlook the potential sub-action temporal structures, resulting in inferior performance. To tackle this problem, we propose a novel sub-action prototype learning framework (SPL-Loc) which comprises Sub-action Prototype Clustering (SPC) and Ordered Prototype Alignment (OPA). SPC adaptively extracts representative sub-action prototypes which are capable to perceive the temporal scale and spatial content variation of action instances. OPA selects relevant prototypes to provide completeness clue for pseudo label generation by applying a temporal alignment loss. As a result, pseudo labels are derived from alignment results to improve action boundary prediction. Extensive experiments on three popular benchmarks demonstrate that the proposed SPL-Loc significantly outperforms existing SOTA PWTAL methods.
Abstract (translated)
点级别的弱监督时间动作定位(PWTAL)旨在为每个行动实例只标注一个 timestamp 注解,以定位每个行动。现有的方法倾向于挖掘密集伪标签以减轻标签稀疏的问题,但忽略了潜在的子行动时间结构,导致性能较差。为了解决这个问题,我们提出了一种新的子行动原型学习框架(SPL-Loc),它包括子行动原型聚类(SPC)和有序原型对齐(OPA)。SPC 自适应地提取具有代表性的子行动原型,能够感知行动实例的时间尺度和空间内容变化。OPA 选择相关的原型,通过应用时间对齐损失来生成伪标签,以提供完整的线索,以改进行动边界预测。在三个流行的基准测试上进行了广泛的实验,结果表明,所提出的 SPL-Loc 显著优于现有的 SOTA PWTAL 方法。
URL
https://arxiv.org/abs/2309.09060