Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities
This work addresses a gap in analyzing complex periodic activities for applications in manufacturing, sports, and daily life, though it is incremental as it builds on prior work on short-term activities.
The paper tackles the problem of detecting long-term periodic workflows in human activities, which are underexplored due to low-contrast patterns, by introducing a benchmark of 580 multimodal sequences and a lightweight baseline that outperforms existing methods in tasks like detection and anomaly elimination.
Periodic human activities with implicit workflows are common in manufacturing, sports, and daily life. While short-term periodic activities -- characterized by simple structures and high-contrast patterns -- have been widely studied, long-term periodic workflows with low-contrast patterns remain largely underexplored. To bridge this gap, we introduce the first benchmark comprising 580 multimodal human activity sequences featuring long-term periodic workflows. The benchmark supports three evaluation tasks aligned with real-world applications: unsupervised periodic workflow detection, task completion tracking, and procedural anomaly detection. We also propose a lightweight, training-free baseline for modeling diverse periodic workflow patterns. Experiments show that: (i) our benchmark presents significant challenges to both unsupervised periodic detection methods and zero-shot approaches based on powerful large language models (LLMs); (ii) our baseline outperforms competing methods by a substantial margin in all evaluation tasks; and (iii) in real-world applications, our baseline demonstrates deployment advantages on par with traditional supervised workflow detection approaches, eliminating the need for annotation and retraining. Our project page is https://sites.google.com/view/periodicworkflow.