mlsanityData to 14 Oct 2026

RoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos

arXiv 2609.17843 ↗First posted 15 Sep 2026cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Video anomaly detection (VAD) is an actively studied task, having wide applications in typical scenarios such as public surveillance and road traffic safety. The task is also relevant for robotic arm interactions, where it has several downstream applications, including learning better interaction and manipulation abilities, triggering recovery procedures when anomalies occur, etc. Despite its relevance, the exploration of anomaly detection in robotic arm manipulation videos is limited by the low number of available resources. To this end, we introduce RoboVAD, a large-scale benchmark for video anomaly detection that comprises challenging cross-domain evaluation scenarios, where certain actions (tasks executed by a robotic arm) and anomaly types (mistakes that occur while performing certain tasks) remain unseen during training. RoboVAD is designed to benchmark VAD methods in realistic scenarios, where robotic arms can perform unforeseen tasks, and thereby encounter new anomaly types. We train and evaluate several state-of-the-art VAD methods, including a novel method specifically adapted for robotic arm manipulation. While the proposed method outperforms many state-of-the-art competitors, all methods remain below a micro-averaged frame-level AUC threshold of 70% in the most challenging evaluation setup, confirming the difficulty of the proposed benchmark. We publicly release our dataset and code at https://zenodo.org/records/22754659.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 55 references that are in the map. First posted on arXiv 15 Sep 2026.

Builds on

45 of 55 references.

References · 45

  1. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  2. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  3. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  4. 2016Learning Temporal Regularity in Video Sequencescited by 254
  5. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  6. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  7. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 138
  8. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  9. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 123
  10. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  11. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 111
  12. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 104
33 more
  1. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  2. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 93
  3. 2019Street Scene: A new dataset and evaluation protocol for video anomaly detectioncited by 90
  4. 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 90
  5. 2020A Survey of Single-Scene Video Anomaly Detectioncited by 88
  6. 2024Harnessing Large Language Models for Training-free Video Anomaly Detectioncited by 87
  7. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 86
  8. 2020Video Cloze Procedure for Self-Supervised Spatio-Temporal Learningcited by 81
  9. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  10. 2026LeRobot: An Open-Source Library for End-to-End Robot Learningcited by 73
  11. 2022Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzlescited by 62
  12. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  13. 2022SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detectioncited by 45
  14. 2022Self-Supervised Masking for Unsupervised Anomaly Detection and Localizationcited by 43
  15. 2023Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectorscited by 37
  16. 2022Self-Supervised Masked Convolutional Transformer Block for Anomaly Detectioncited by 34
  17. 2018Detecting abnormal events in video using Narrowed Normality Clusterscited by 30
  18. 2023ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulationcited by 18
  19. 2025AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLMcited by 15
  20. 2025Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbolscited by 14
  21. 2020FINO-Net: A Deep Multimodal Sensor Fusion Framework for Manipulation Failure Detectioncited by 13
  22. 2025MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detectioncited by 11
  23. 2020Decoupled Appearance and Motion Learning for Efficient Anomaly Detection in Surveillance Videocited by 9
  24. 2025Language-guided Open-world Video Anomaly Detection under Weak Supervisioncited by 8
  25. 2025Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignmentcited by 8
  26. 2021Using Visual Anomaly Detection for Task Execution Monitoringcited by 7
  27. 2025ConditionNET: Learning Preconditions and Effects for Execution Monitoringcited by 7
  28. 2024A Multimodal Handover Failure Detection Dataset and Baselinescited by 6
  29. 2026Failure Identification in Imitation Learning Via Statistical and Semantic Filteringcited by 6
  30. 2021An Efficient Approach for Anomaly Detection in Traffic Videoscited by 5
  31. 2026Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoningcited by 3
  32. 2022Object-centric and memory-guided normality reconstruction for video anomaly detectioncited by 2
  33. 2025FrameShield: Adversarially Robust Video Anomaly Detectioncited by 2

Built on by

Not cited yet.