Sensing Anomalies like Humans: A Hominine Framework to Detect Abnormal Events from Unlabeled Videos

• URL: http://arxiv.org/abs/2108.01975v1
• Date: Wed, 4 Aug 2021 11:31:57 GMT
• Title: Sensing Anomalies like Humans: A Hominine Framework to Detect Abnormal Events from Unlabeled Videos
• Abstract summary: Video anomaly detection (VAD) has constantly been a vital topic in video analysis. We are inspired by how humans sense anomalies and propose a hominine framework that enables both unsupervised and end-to-end VAD.
• Score: 48.15740415466055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video anomaly detection (VAD) has constantly been a vital topic in video analysis. As anomalies are often rare, it is typically addressed under a semi-supervised setup, which requires a training set with pure normal videos. To avoid exhausted manual labeling, we are inspired by how humans sense anomalies and propose a hominine framework that enables both unsupervised and end-to-end VAD. The framework is based on two key observations: 1) Human perception is usually local, i.e. focusing on local foreground and its context when sensing anomalies. Thus, we propose to impose locality-awareness by localizing foreground with generic knowledge, and a region localization strategy is designed to exploit local context. 2) Frequently-occurred events will mould humans' definition of normality, which motivates us to devise a surrogate training paradigm. It trains a deep neural network (DNN) to learn a surrogate task with unlabeled videos, and frequently-occurred events will play a dominant role in "moulding" the DNN. In this way, a training loss gap will automatically manifest rarely-seen novel events as anomalies. For implementation, we explore various surrogate tasks as well as both classic and emerging DNN models. Extensive evaluations on commonly-used VAD benchmarks justify the framework's applicability to different surrogate tasks or DNN models, and demonstrate its astonishing effectiveness: It not only outperforms existing unsupervised solutions by a wide margin (8% to 10% AUROC gain), but also achieves comparable or even superior performance to state-of-the-art semi-supervised counterparts.

Related papers

• Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection [50.343419243749054]
  Anomaly detection is critical in fields such as medical diagnostics and industrial defect detection.<n> CLIP's coarse-grained image-text alignment limits localization and detection performance for fine-grained anomalies.<n>Crane improves the state-of-the-art ZSAD from 2% to 28%, at both image and pixel levels, while remaining competitive in inference speed.
  arXiv  Detail & Related papers  (2025-04-15T10:42:25Z)
• CRCL: Causal Representation Consistency Learning for Anomaly Detection in Surveillance Videos [40.63347505454772]
  Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community. Previous methods only use easily collected regular events to model the inherent normality of normal spatial-temporal patterns in an unsupervised manner. We propose Causal Consistency Representation Learning (CRCL) to implicitly mine potential scene-robust causal variable in unsupervised video normality learning.
  arXiv  Detail & Related papers  (2025-03-24T15:50:19Z)
• Temporal Divide-and-Conquer Anomaly Actions Localization in Semi-Supervised Videos with Hierarchical Transformer [0.9208007322096532]
  Anomaly action detection and localization play an essential role in security and advanced surveillance systems. We propose a hierarchical transformer model designed to evaluate the significance of observed actions in anomalous videos. Our approach segments a parent video hierarchically into multiple temporal children instances and measures the influence of the children nodes in classifying the abnormality of the parent video.
  arXiv  Detail & Related papers  (2024-08-24T18:12:58Z)
• Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts [57.01985221057047]
  This paper introduces a novel method that learnstemporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs) Our method achieves state-of-theart performance on three public benchmarks for the WSVADL task.
  arXiv  Detail & Related papers  (2024-08-12T03:31:29Z)
• GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features [68.14842693208465]
  GeneralAD is an anomaly detection framework designed to operate in semantic, near-distribution, and industrial settings. We propose a novel self-supervised anomaly generation module that employs straightforward operations like noise addition and shuffling to patch features. We extensively evaluated our approach on ten datasets, achieving state-of-the-art results in six and on-par performance in the remaining.
  arXiv  Detail & Related papers  (2024-07-17T09:27:41Z)
• Open-Vocabulary Video Anomaly Detection [57.552523669351636]
  Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. Recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies.
  arXiv  Detail & Related papers  (2023-11-13T02:54:17Z)
• LGN-Net: Local-Global Normality Network for Video Anomaly Detection [9.578697308678153]
  Video detection (VAD) has been intensively studied for years of its potential applications in intelligent video systems unsupervised. Existing VAD methods tend to learn normality from training sets consisting of only normal videos. We propose a two-branch model Local Normality Network (LG-Net) to learn local and global normality simultaneously.
  arXiv  Detail & Related papers  (2022-11-14T15:32:08Z)
• Detecting and Learning the Unknown in Semantic Segmentation [4.970364068620608]
  Semantic segmentation is a crucial component for perception in automated driving. Deep neural networks (DNNs) are commonly used for this task and they are usually trained on a closed set of object classes appearing in a closed operational domain. In this work, we first give an overview about anomalies from an information-theoretic perspective. We review research in detecting semantically unknown objects in semantic segmentation. We demonstrate that training for high entropy responses on anomalous objects outperforms other recent methods.
  arXiv  Detail & Related papers  (2022-02-17T15:07:24Z)
• Anomaly Crossing: A New Method for Video Anomaly Detection as Cross-domain Few-shot Learning [32.0713939637202]
  Video anomaly detection aims to identify abnormal events that occurred in videos. Most previous approaches learn only from normal videos using unsupervised or semi-supervised methods. We propose a new learning paradigm by making full use of both normal and abnormal videos for video anomaly detection.
  arXiv  Detail & Related papers  (2021-12-12T20:49:38Z)
• A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video [120.18562044084678]
  Abnormal event detection in video is a complex computer vision problem that has attracted significant attention in recent years. We propose a background-agnostic framework that learns from training videos containing only normal events.
  arXiv  Detail & Related papers  (2020-08-27T18:39:24Z)
• Localizing Anomalies from Weakly-Labeled Videos [45.58643708315132]
  We propose a WeaklySupervised Anomaly localization (WSAL) method focusing on temporally localizing anomalous segments within anomalous videos. Inspired by the appearance difference in anomalous videos, the evolution of adjacent temporal segments is evaluated for the localization of anomalous segments. Our proposed method achieves new state-of-the-art performance on the UCF-Crime and TAD datasets.
  arXiv  Detail & Related papers  (2020-08-20T12:58:03Z)
• Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection [114.9714355807607]
  We show that applying self-trained deep ordinal regression to video anomaly detection overcomes two key limitations of existing methods. We devise an end-to-end trainable video anomaly detection approach that enables joint representation learning and anomaly scoring without manually labeled normal/abnormal data.
  arXiv  Detail & Related papers  (2020-03-15T08:44:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.