O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Mei Yuan, Qi Long, Qifeng Wu, Zhenyang Li, Yizhou Zhao, Lei Wang, Yang Liu, Min Xu
• Venue: arXiv: cs.CV
• Published: 2026-07-20
• Collected: 2026-07-21
• URL: http://arxiv.org/abs/2607.18142v1
• PDF: https://arxiv.org/pdf/2607.18142v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers have developed a new method for detecting abnormal objects and events in industrial settings using an object-centric tracking and reasoning approach. This method is designed to overcome the limitations of existing methods, particularly those that rely on retraining or domain-specific knowledge.

What the Document Says

• The research focuses on Industrial Video Anomaly Detection (IVAD).
• Existing VLM-based anomaly reasoning methods perform poorly in industrial settings due to intricate object transformations, strict physics, and procedural constraints.
• A new agentic framework for anomaly detection is introduced. This framework is training-free, focuses on object state evolution, and does not require domain-specific knowledge.
• The method tracks spatial-temporal dynamics and underlying transformations of detected objects over time.
• It reasons over the object-wise temporal state trajectories to identify abnormal objects in grounded frames.
• The new method addresses limitations of prior approaches that rely on retraining on normal clips or injecting domain knowledge as context for test-time inference.
• Experiments show that the new method outperforms existing VLMs, agentic frameworks, and traditional VAD methods fine-tuned on the respective datasets.
• The method provides interpretable reports over anomaly processes and types.

Key Concepts Mentioned

• Industrial Video Anomaly Detection
• VLM-based anomaly reasoning
• object-centric tracking and reasoning
• agentic framework
• retraining
• domain-specific knowledge
• spatial-temporal dynamics
• grounded frames
• abnormal objects

Claims Made by the Document

• The new method outperforms existing VLMs, agentic frameworks, and traditional VAD methods.

Evidence Used

• Extensive experiments on three IVAD datasets

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Industrial Video Anomaly Detection (IVAD) aims to identify anomalous objects and events in an industrial process, which is crucial for modern manufacturing and quality control systems. Existing VLM-based anomaly reasoning methods are capable of detecting open-ended anomalies in general domains. However, their performance declines in industrial settings characterized by intricate object transformations, strict physics, and procedural constraints. To tackle the complexity of such interaction-intensive detection, we introduce a training-free agentic framework for anomaly detection free of domain-specific knowledge, emphasizing object state evolution like humans inspectors. It is designed to track spatial-temporal dynamics and underlying transformations of detected objects over time, and then reason over the object-wise temporal state trajectories to identify abnormal objects in grounded frames. Our method overcomes limitations of prior approaches that rely on retraining on normal clips or injecting domain knowledge as context for test-time inference. Extensive experiments on three IVAD datasets demonstrate that our method outperforms frontier VLMs, agentic frameworks, and traditional VAD methods fine-tuned on the respective datasets, while providing interpretable reports over anomaly processes and types.