Feature prediction diffusion model for video anomaly detection

Anomaly detection in the video is an important research area and a challenging task in real applications. Due to the unavailability of large-scale annotated anomaly events, most existing video anomaly detection (VAD) methods focus on learning the distribution of normal samples to detect the substant...

Full description

Saved in:
Bibliographic Details
Main Authors: YAN, Cheng, ZHANG, Shiyu, LIU, Yang, PANG, Guansong, WANG, Wenjun
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8414
https://ink.library.smu.edu.sg/context/sis_research/article/9417/viewcontent/Yan_Feature_Prediction_Diffusion_Model_for_Video_Anomaly_Detection_ICCV_2023_paper.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9417
record_format dspace
spelling sg-smu-ink.sis_research-94172024-01-09T03:45:24Z Feature prediction diffusion model for video anomaly detection YAN, Cheng ZHANG, Shiyu LIU, Yang PANG, Guansong WANG, Wenjun Anomaly detection in the video is an important research area and a challenging task in real applications. Due to the unavailability of large-scale annotated anomaly events, most existing video anomaly detection (VAD) methods focus on learning the distribution of normal samples to detect the substantially deviated samples as anomalies. To well learn the distribution of normal motion and appearance, many auxiliary networks are employed to extract foreground object or action information. These high-level semantic features effectively filter the noise from the background to decrease its influence on detection models. However, the capability of these extra semantic models heavily affects the performance of the VAD methods. Motivated by the impressive generative and anti-noise capacity of diffusion model (DM), in this work, we introduce a novel DM-based method to predict the features of video frames for anomaly detection. We aim to learn the distribution of normal samples without any extra high-level semantic feature extraction models involved. To this end, we build two denoising diffusion implicit modules to predict and refine the features. The first module concentrates on feature motion learning, while the last focuses on feature appearance learning. To the best of our knowledge, it is the first DM-based method to predict frame features for VAD. The strong capacity of DMs also enables our method to more accurately predict the normal features than non-DM-based feature prediction-based VAD methods. Extensive experiments show that the proposed approach substantially outperforms state-of-the-art competing methods. 2023-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8414 https://ink.library.smu.edu.sg/context/sis_research/article/9417/viewcontent/Yan_Feature_Prediction_Diffusion_Model_for_Video_Anomaly_Detection_ICCV_2023_paper.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Artificial Intelligence and Robotics Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
spellingShingle Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
YAN, Cheng
ZHANG, Shiyu
LIU, Yang
PANG, Guansong
WANG, Wenjun
Feature prediction diffusion model for video anomaly detection
description Anomaly detection in the video is an important research area and a challenging task in real applications. Due to the unavailability of large-scale annotated anomaly events, most existing video anomaly detection (VAD) methods focus on learning the distribution of normal samples to detect the substantially deviated samples as anomalies. To well learn the distribution of normal motion and appearance, many auxiliary networks are employed to extract foreground object or action information. These high-level semantic features effectively filter the noise from the background to decrease its influence on detection models. However, the capability of these extra semantic models heavily affects the performance of the VAD methods. Motivated by the impressive generative and anti-noise capacity of diffusion model (DM), in this work, we introduce a novel DM-based method to predict the features of video frames for anomaly detection. We aim to learn the distribution of normal samples without any extra high-level semantic feature extraction models involved. To this end, we build two denoising diffusion implicit modules to predict and refine the features. The first module concentrates on feature motion learning, while the last focuses on feature appearance learning. To the best of our knowledge, it is the first DM-based method to predict frame features for VAD. The strong capacity of DMs also enables our method to more accurately predict the normal features than non-DM-based feature prediction-based VAD methods. Extensive experiments show that the proposed approach substantially outperforms state-of-the-art competing methods.
format text
author YAN, Cheng
ZHANG, Shiyu
LIU, Yang
PANG, Guansong
WANG, Wenjun
author_facet YAN, Cheng
ZHANG, Shiyu
LIU, Yang
PANG, Guansong
WANG, Wenjun
author_sort YAN, Cheng
title Feature prediction diffusion model for video anomaly detection
title_short Feature prediction diffusion model for video anomaly detection
title_full Feature prediction diffusion model for video anomaly detection
title_fullStr Feature prediction diffusion model for video anomaly detection
title_full_unstemmed Feature prediction diffusion model for video anomaly detection
title_sort feature prediction diffusion model for video anomaly detection
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/8414
https://ink.library.smu.edu.sg/context/sis_research/article/9417/viewcontent/Yan_Feature_Prediction_Diffusion_Model_for_Video_Anomaly_Detection_ICCV_2023_paper.pdf
_version_ 1787590771691487232