Alleviating noisy pseudo labels remains a key challenge in Semi-Supervised Temporal Action Localization (SS-TAL). Existing methods often filter pseudo labels based on strict conditions, but they typically assess classification and localization quality separately, leading to suboptimal pseudo-label ranking and selection. In particular, there might be inaccurate pseudo labels within selected positives, alongside reliable counterparts erroneously assigned to negatives. To tackle these problems, we propose a novel Adaptive Pseudo-label Learning (APL) framework to facilitate better pseudo-label selection. Specifically, to improve the ranking quality, Adaptive Label Quality Assessment (ALQA) is proposed to jointly learn classification confidence and localization reliability, followed by dynamically selecting pseudo labels based on the joint score. Additionally, we propose an Instance-level Consistency Discriminator (ICD) for eliminating ambiguous positives and mining potential positives simultaneously based on inter-instance intrinsic consistency, thereby leading to a more precise selection. We further introduce a general unsupervised Action-aware Contrastive Pre-training (ACP) to enhance the discrimination both within actions and between actions and backgrounds, which benefits SS-TAL. Extensive experiments on THUMOS14 and ActivityNet v1.3 demonstrate that our method achieves state-of-the-art performance under various semi-supervised settings.

翻译：缓解噪声伪标签仍是半监督时序动作定位（SS-TAL）中的关键挑战。现有方法通常基于严格条件过滤伪标签，但它们往往分别评估分类质量与定位质量，导致伪标签排序与选择欠优。具体而言，在选定的正样本中可能存在不准确的伪标签，同时部分可靠的样本却被错误地归入负样本。为解决这些问题，我们提出一种新颖的自适应伪标签学习（APL）框架，以促进更好的伪标签选择。具体来说，为提升排序质量，我们提出自适应标签质量评估（ALQA），以联合学习分类置信度与定位可靠性，并依据联合得分动态选择伪标签。此外，我们提出实例级一致性判别器（ICD），基于实例间的内在一致性同时消除模糊正样本并挖掘潜在正样本，从而实现更精确的选择。我们进一步引入一种通用的无监督动作感知对比预训练（ACP）方法，以增强动作内部以及动作与背景之间的区分性，从而提升SS-TAL性能。在THUMOS14和ActivityNet v1.3数据集上的大量实验表明，本方法在各种半监督设定下均取得了最先进的性能。