arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.05511cs.CV
收藏

基于提议的点级监督时序动作定位

Proposal-based Temporal Action Localization with Point-level Supervision

Yuan Yin, Yifei Huang, Ryosuke Furuta, Yoichi Sato

AI总结:

针对点级监督时序动作定位中MIL框架依赖短片段、信息有限的问题,提出基于灵活时长动作提议的定位方法,结合高效聚类生成密集伪标签与细粒度对比损失优化,在四个基准上取得媲美甚至超越现有最优及部分全监督方法的性能。

摘要:

点级监督时序动作定位(PTAL)旨在识别并定位未修剪视频中的动作,训练数据中仅标注了每个动作实例内的单个点(帧)。在没有时序标注的情况下,以往多数工作采用多示例学习(MIL)框架,该框架将输入视频分割为不重叠的短片段,并对每个短片段独立进行动作分类。我们认为MIL框架对于PTAL而言并非最优,因为它基于包含有限时序信息的独立短片段运行。因此,分类器仅关注若干易于区分的片段,而非发现完整的动作实例且不遗漏任何相关片段。为缓解这一问题,我们提出一种新方法,通过生成并评估时长灵活、包含更全面时序信息的动作提议来定位动作。此外,我们引入了一种高效的聚类算法,可高效生成提供更强监督的密集伪标签,还引入了细粒度对比损失以进一步优化伪标签质量。实验表明,我们提出的方法在ActivityNet 1.3、THUMOS 14、GTEA和BEOID四个基准数据集上,取得了与现有最优方法及部分全监督方法相当甚至更优的性能。

英文摘要:

Point-level supervised temporal action localization (PTAL) aims at recognizing and localizing actions in untrimmed videos where only a single point (frame) within every action instance is annotated in training data. Without temporal annotations, most previous works adopt the multiple instance learning (MIL) framework, where the input video is segmented into non-overlapped short snippets, and action classification is performed independently on every short snippet. We argue that the MIL framework is suboptimal for PTAL because it operates on separated short snippets that contain limited temporal information. Therefore, the classifier only focuses on several easy-to-distinguish snippets instead of discovering the whole action instance without missing any relevant snippets. To alleviate this problem, we propose a novel method that localizes actions by generating and evaluating action proposals of flexible duration that involve more comprehensive temporal information. Moreover, we introduce an efficient clustering algorithm to efficiently generate dense pseudo labels that provide stronger supervision, and a fine-grained contrastive loss to further refine the quality of pseudo labels. Experiments show that our proposed method achieves competitive or superior performance to the state-of-the-art methods and some fully-supervised methods on four benchmarks: ActivityNet 1.3, THUMOS 14, GTEA, and BEOID datasets.

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。

↑