Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911277279870976 |
|---|---|
| author | Yang, Fan Xie, Quanting Moteki, Atsunori Masui, Shoichi Jiang, Shan Uchino, Kanji Bisk, Yonatan Neubig, Graham |
| author_facet | Yang, Fan Xie, Quanting Moteki, Atsunori Masui, Shoichi Jiang, Shan Uchino, Kanji Bisk, Yonatan Neubig, Graham |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14945 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities Yang, Fan Xie, Quanting Moteki, Atsunori Masui, Shoichi Jiang, Shan Uchino, Kanji Bisk, Yonatan Neubig, Graham Computer Vision and Pattern Recognition 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. |
| title | Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.14945 |