发表机构
AIGO Unit, Istituto Italiano di Tecnologia; Department of Computer Science, University of Verona; University of Genoa（意大利技术研究院AIGO单元; 维罗纳大学计算机科学系; 热那亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出TReViS，一种利用时间自相似矩阵估计重复结构并合成伪标签视频的自监督框架，无需标签即可训练重复动作计数模型，性能媲美监督方法。
AI 中文摘要
全监督重复动作计数（RAC）已取得强劲性能，但需要密集的时间标注，成本高昂且难以扩展。我们提出TReViS，一种自监督视频合成框架，无需任何重复标签即可训练RAC模型。TReViS通过时间自相似矩阵估计未标记视频的潜在时序重复结构，推断其周期统计信息，并合成新的训练序列，这些序列在保留真实重复模式的同时引入受控的时间变异性。这些合成视频与伪标签配对，用于从头训练现有的RAC架构。在多个数据集和骨干网络上，TReViS持续优于先前的自监督方法，并与若干监督基线性能相当，同时完全无需标签，展示了结构感知视频合成对无标签RAC的有效性。源代码可在该https URL获取。
英文摘要
Fully supervised repetitive action counting (RAC) has achieved strong performance, but requires dense temporal annotations that are costly and difficult to scale. We propose TReViS, a self-supervised video synthesis framework that enables training RAC models without any repetition labels. TReViS estimates the underlying temporal repetition structure of an unlabeled video via a Temporal Self-Similarity Matrix, infers its cycle statistics, and synthesizes new training sequences that preserve realistic repetition patterns while introducing controlled temporal variability. These synthesized videos are paired with pseudo-labels and used to train existing RAC architectures from scratch. Across multiple datasets and backbones, TReViS consistently outperforms prior self-supervised methods and achieves performance competitive with several supervised baselines, while remaining fully label-free, demonstrating the effectiveness of structure-aware video synthesis for label-free RAC. The source code is available at https://github.com/yfqi/TReViS.
CommentsAccepted for publication in Image and Vision Computing (Elsevier). This is the author-accepted manuscript and not the final published version of record. The DOI and link to the published version will be added when available
