Fan Yang*, Quanting Xie†, Atsunori Moteki*, Shoichi Masui*, Shan Jiang*, Kanji Uchino*,
Yonatan Bisk†, and Graham Neubig†
* Fujitsu Research, † Carnegie Mellon University
This paper is presented at WACV 2026 as an oral paper (oral acceptance rate: 87/2,458=3.5% ). It investigates three fundamental problems in modeling periodic spatiotemporal human activities:
Whether human activity workflows can be inferred from unlabeled periodic data.
How to formally define atomic human activity tokens and compose them into structured workflows.
How such activity workflows can be operationalized in real-world applications.
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.
Periodic spatiotemporal activity in a yoga example. While existing studies focus on short-term periods with simple structures and high-contrast patterns, we investigate a novel direction on long-term periods that involve complex workflows with low-contrast patterns.
Left: Illustration of our benchmark. TopRight: Statistics of our dataset. BottomRight: Annotation of our benchmark. We collected 580 long-term workflows of periodic human activities, characterized by a compact dataset yet encompassing a wide variety of real-world periodic tasks, including factory production, exercise training, and shuttle routes.
@InProceedings{Fan_2026_WACV,
author = {Fan, Yang and Quanting, Xie and Atsunori, Moteki and Shoichi, Masui and Shan, Jiang and Yonatan, Bisk and Graham, Neubig},
title = {Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities},
booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2026}
}