VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914337732427776 |
|---|---|
| author | Yang, Yingyuan Lan, Tian Gao, Yifei Lu, Yimeng He, Wenjun Wang, Meng Liu, Chenghao Zhang, Chen |
| author_facet | Yang, Yingyuan Lan, Tian Gao, Yifei Lu, Yimeng He, Wenjun Wang, Meng Liu, Chenghao Zhang, Chen |
| contents | Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundation models face a fundamental trade-off: 1D temporal models provide fine-grained pointwise localization but lack a global contextual perspective, while 2D vision-based models capture global patterns but suffer from information bottlenecks due to a lack of temporal alignment and coarse-grained pointwise detection. To resolve this dilemma, we propose VETime, the first TSAD framework that unifies temporal and visual modalities through fine-grained visual-temporal alignment and dynamic fusion. VETime introduces a Reversible Image Conversion and a Patch-Level Temporal Alignment module to establish a shared visual-temporal timeline, preserving discriminative details while maintaining temporal sensitivity. Furthermore, we design an Anomaly Window Contrastive Learning mechanism and a Task-Adaptive Multi-Modal Fusion to adaptively integrate the complementary perceptual strengths of both modalities. Extensive experiments demonstrate that VETime significantly outperforms state-of-the-art models in zero-shot scenarios, achieving superior localization precision with lower computational overhead than current vision-based approaches. Code available at: https://github.com/yyyangcoder/VETime. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16681 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection Yang, Yingyuan Lan, Tian Gao, Yifei Lu, Yimeng He, Wenjun Wang, Meng Liu, Chenghao Zhang, Chen Computer Vision and Pattern Recognition Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundation models face a fundamental trade-off: 1D temporal models provide fine-grained pointwise localization but lack a global contextual perspective, while 2D vision-based models capture global patterns but suffer from information bottlenecks due to a lack of temporal alignment and coarse-grained pointwise detection. To resolve this dilemma, we propose VETime, the first TSAD framework that unifies temporal and visual modalities through fine-grained visual-temporal alignment and dynamic fusion. VETime introduces a Reversible Image Conversion and a Patch-Level Temporal Alignment module to establish a shared visual-temporal timeline, preserving discriminative details while maintaining temporal sensitivity. Furthermore, we design an Anomaly Window Contrastive Learning mechanism and a Task-Adaptive Multi-Modal Fusion to adaptively integrate the complementary perceptual strengths of both modalities. Extensive experiments demonstrate that VETime significantly outperforms state-of-the-art models in zero-shot scenarios, achieving superior localization precision with lower computational overhead than current vision-based approaches. Code available at: https://github.com/yyyangcoder/VETime. |
| title | VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.16681 |