Experiments show that CAPS achieves the strongest aggregate performance across all four evaluation metrics among the compared methods, while complementary ablations and transfer analyses support the roles of context anchoring, semantic disentanglement, and conditional realization.
Abstract
Time series anomaly detection (TSAD) remains challenging not only because anomaly labels are scarce, but also because temporal anomalies are highly context-dependent. Existing methods often rely on unsupervised objectives or surrogate abnormal patterns, providing limited supervision for context-dependent normal--anomalous distinctions. We propose Context-Anchored Pair Supervision (CAPS), a supervision-recovery framework for TSAD. CAPS views ideal anomaly supervision as a matched comparison between normal and anomalous outcomes under the same temporal context, and seeks to recover such supervision without target-domain anomaly labels. Using simulated normal--anomalous pairs, CAPS learns structure and anomaly-semantic representations through reconstruction, background consistency, and within-pair counterfactual recombination. The resulting anomaly representations form a continuous semantic space with coarse modes and induce a sampleable multimodal prior. CAPS conditionally realizes sampled semantics as residual-form effects on target reference trajectories. The resulting context-anchored normal--anomalous counterparts provide temporal supervision for discriminative detector learning. Experiments on nine datasets show that CAPS achieves the strongest aggregate performance across all four evaluation metrics among the compared methods, while complementary ablations and transfer analyses support the roles of context anchoring, semantic disentanglement, and conditional realization.
Reconstruction errors in multivariate time-series anomaly detection may not reliably distinguish abnormal behavior from benign deviations. Language-derived semantics offer complementary context, but existing multimodal approaches may rely on time-associated paired textual information that is difficult to obtain consist...
Jahyeob Koo, Kio Yun, Byoung-Mo Koo et al.· arXiv.org· 0 citations
Transformer with Variational AutoEncoder is presented, a framework that combines a dual-embedding representation pipeline, a Transformer encoder for long-range dependency modeling, and VAE-based latent regularization of encoded features to provide an effective and robust solution for long-term time-series anomaly detec...
Xian-Kun Shi, Yi-Bo Li, Zi-Qi Wang et al.· CAAI Artificial Intelligence...· 0 citations
CAST is proposed, a Context- and Anomaly Structure-conditioned Time series anomaly generation framework with principled two-stage pretraining and finetuning strategy that consistently outperforms state-of-the-art anomaly generation methods in terms of both generation fidelity and downstream task utility.
H. Zhang, Jie Peng, Song-Yuan Sui et al.· 0 citations
This paper proposes CHAIN (long-Context History-supervised Anomaly detectIoN), a novel framework that explicitly captures long-term historical contexts under anomaly simulation and supervises current-window anomaly detection via masked cross-attention fusion.
Time series anomaly detection faces a critical challenge that different anomaly types require different detection mechanisms, yet single methods are inherently limited by their design biases. We propose FlowFuse, a multi-view ensemble framework with coupling flow-based score fusion for time series anomaly detection. Fl...
Wanghui Qiu, Chen-Xi Liu, Shiyan Hu et al.· Proceedings of the Thirty-Fi...· 0 citations
In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly prompts difficult to learn from these samples alone. Some vision-language methods therefore use manually specified descriptions to supply explicit anomaly semantics. However, constructing these de...
Meng-Yang Zhao, Teng Fu, Hai-Yang Yu et al.· 0 citations