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

Hugging Face Daily Papers Papers
industrial-video-anomaly-detection object-centric-tracking training-free agentic-framework vlm anomaly-reasoning open-ended-anomalies

Summary

O-VAD introduces a training-free agentic framework for industrial video anomaly detection that tracks object state evolution over time and reasons over temporal trajectories to identify abnormal objects, outperforming existing VLM and VAD methods on three datasets.

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.
Original Article
View Cached Full Text

Cached at: 07/27/26, 05:45 PM

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

Source: https://huggingface.co/papers/2607.18142

Abstract

IndustrialVideoAnomalyDetection(IVAD)aimstoidentifyanomalousobjectsandeventsinanindustrialprocess,whichiscrucialformodernmanufacturingandqualitycontrolsystems.ExistingVLM-basedanomalyreasoningmethodsarecapableofdetectingopen-endedanomaliesingeneraldomains.However,theirperformancedeclinesinindustrialsettingscharacterizedbyintricateobjecttransformations,strictphysics,andproceduralconstraints.Totacklethecomplexityofsuchinteraction-intensivedetection,weintroduceatraining-freeagenticframeworkforanomalydetectionfreeofdomain-specificknowledge,emphasizingobjectstateevolutionlikehumansinspectors.Itisdesignedtotrackspatial-temporaldynamicsandunderlyingtransformationsofdetectedobjectsovertime,andthenreasonovertheobject-wisetemporalstatetrajectoriestoidentifyabnormalobjectsingroundedframes.Ourmethodovercomeslimitationsofpriorapproachesthatrelyonretrainingonnormalclipsorinjectingdomainknowledgeascontextfortest-timeinference.ExtensiveexperimentsonthreeIVADdatasetsdemonstratethatourmethodoutperformsfrontierVLMs,agenticframeworks,andtraditionalVADmethodsfine-tunedontherespectivedatasets,whileprovidinginterpretablereportsoveranomalyprocessesandtypes.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2607\.18142

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.18142 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.18142 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.18142 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles