Anomaly and activity recognition in a video surveillance using Masked Autoencoder

Datchanamoorthy, Kavitha; Padmavathi, B.; Prakash, Vishnu; Yogesh, Sharma; R, Sikkandar Sahabudeen

doi:10.1109/icses55317.2022.9914213

Cited by 2 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, half of the patches in the STC are masked along the temporal dimension, and a ViT is trained to predict the masked patches using the unmasked patches. [114] (2022.10) further uses MAE for recognizing anomalous human activities.…”

Section: Video Prediction and Surveillancementioning

confidence: 99%

Masked Autoencoders in Computer Vision: A Comprehensive Survey

Zhou,

Liu

2023

IEEE Access

View full text Add to dashboard Cite

Masked autoencoders (MAE) is a deep learning method based on Transformer. Originally used for images, it has now been extended to video, audio, and some other temporal prediction tasks. In the field of computer vision, MAE performs well in classification, prediction, and target detection tasks. In terms of specific application, MAE has made many achievements in medical treatment, geography, 3D point cloud and machine troubleshooting. Since its introduction at the end of 2021, there have been more than 300 related preprints, and MAE has been significantly performed in tier one computer vision conferences during 2022 and 2023. In view of the current popularity of MAE and its future development prospects, we conduct a relatively comprehensive survey of MAE mainly covering officially published articles so far. We comb through and classify the improvements in MAE, demonstrating relatively representative applications in computer vision. Finally, as a summary, we discuss the possible future research directions and development areas based on the characteristics of MAE, hoping our work could be a reference for the future work of MAE.INDEX TERMS Computer vision survey, MAE, masked autoencoders, masked image modeling.

show abstract

Section: Video Prediction and Surveillancementioning

confidence: 99%

Masked Autoencoders in Computer Vision: A Comprehensive Survey

Zhou,

Liu

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…AEs ( [53]), ( [117]) , ( [81]) have a wide range of applications, including image generation, data compression, denoising, anomaly detection, image inpainting, recommender systems, drug discovery, and text generation. Their ability to learn a lowerdimensional latent representation of complex data makes them versatile tools for various tasks across different domains.…”

Section: ) Applicationsmentioning

confidence: 99%

“…• Activity recognition ( [53]): AEs can be used to learn features from video data for recognizing and classifying human activities or gestures. This can aid in detecting unusual behavior or identifying specific actions that may be relevant to security issues.…”

Section: ) Applicationsmentioning

confidence: 99%

A Comprehensive Survey of Machine Learning Methods for Surveillance Videos Anomaly Detection

Choudhry,

Abawajy,

Huda

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Video Surveillance Systems (VSSs) are used in a wide range of applications including public safety and perimeter security. They are deployed in places such as markets, hospitals, schools, banks, shopping malls, offices, and smart cities. VSSs generate a massive amount of surveillance data, and significant research has been published on the use of machine learning algorithms to handle surveillance data. In this paper, we present an extensive overview and a thorough analysis of cutting-edge learning methods used in VSSs. Existing surveys on learning approaches in video surveillance have some drawbacks, such as a lack of in-depth analysis of the learning algorithms, omission of certain methodologies, insufficient critical evaluation, and absence of recent learning algorithms. To fill these gaps, this survey provides a thorough examination of the most recent learning algorithms for anomaly detection. A critical assessment of the algorithms including their strengths, weaknesses, and applicability as well as tailored classifications of anomaly types for different domains are provided. Our study also offers insights into the future development of learning techniques in VSS, positioning itself as a valuable resource for both researchers and practitioners in the field. Finally, we share our thoughts on what we learned and how it can help with new developments in the future.

show abstract

Anomaly and activity recognition in a video surveillance using Masked Autoencoder

Cited by 2 publications

References 13 publications

Masked Autoencoders in Computer Vision: A Comprehensive Survey

Masked Autoencoders in Computer Vision: A Comprehensive Survey

A Comprehensive Survey of Machine Learning Methods for Surveillance Videos Anomaly Detection

Contact Info

Product

Resources

About