VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection

2026-02-18

AI Summary

This work addresses the challenge in time series anomaly detection where point anomalies and contextual anomalies are difficult to capture simultaneously, and fine-grained localization often conflicts with global context awareness. To overcome this trade-off, the authors propose a zero-shot anomaly detection method that synergistically integrates the strengths of one-dimensional temporal modeling and two-dimensional visual representation. By leveraging invertible image transformation and block-level temporal alignment, a shared visual-temporal timeline is constructed. The approach further incorporates anomaly window contrastive learning and a task-adaptive multimodal fusion mechanism to achieve precise anomaly localization. Evaluated under a zero-shot setting, the proposed method significantly outperforms current state-of-the-art models while maintaining lower computational overhead than existing vision-based approaches.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Web data visualization

Abstract

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.

Problem

• Time-series anomaly detection
• Point Anomalies
• Context Anomalies
• Temporal alignment
• Zero-shot learning

Innovation

• Zero-Shot Time Series Anomaly Detection
• Visual-Temporal Alignment
• Multi-Modal Fusion
• Patch-Level Temporal Alignment
• Anomaly Window Contrastive Learning