Open Access

ARTICLE

Enhancing Anomaly Detection with Causal Reasoning and Semantic Guidance

Weishan Gao^1,2, Ye Wang^1,2, Xiaoyin Wang^1,2, Xiaochuan Jing^1,2,*

1 China Aerospace Academy of Systems Science and Engineering, Beijing, 100048, China
2 Aerospace Hongka Intelligent Technology (Beijing) Co., Ltd., Beijing, 100048, China

* Corresponding Author: Xiaochuan Jing. Email:

Computers, Materials & Continua 2026, 86(3), 84 https://doi.org/10.32604/cmc.2025.073850

Received 27 September 2025; Accepted 05 November 2025; Issue published 12 January 2026

Abstract

In the field of intelligent surveillance, weakly supervised video anomaly detection (WSVAD) has garnered widespread attention as a key technology that identifies anomalous events using only video-level labels. Although multiple instance learning (MIL) has dominated the WSVAD for a long time, its reliance solely on video-level labels without semantic grounding hinders a fine-grained understanding of visually similar yet semantically distinct events. In addition, insufficient temporal modeling obscures causal relationships between events, making anomaly decisions reactive rather than reasoning-based. To overcome the limitations above, this paper proposes an adaptive knowledge-based guidance method that integrates external structured knowledge. The approach combines hierarchical category information with learnable prompt vectors. It then constructs continuously updated contextual references within the feature space, enabling fine-grained meaning-based guidance over video content. Building on this, the work introduces an event relation analysis module. This module explicitly models temporal dependencies and causal correlations between video snippets. It constructs an evolving logic chain of anomalous events, revealing the process by which isolated anomalous snippets develop into a complete event. Experiments on multiple benchmark datasets show that the proposed method achieves highly competitive performance, achieving an AUC of 88.19% on UCF-Crime and an AP of 86.49% on XD-Violence. More importantly, the method provides temporal and causal explanations derived from event relationships alongside its detection results. This capability significantly advances WSVAD from a simple binary classification to a new level of interpretable behavior analysis.

---

Keywords

---