Video Anomaly Detection by Estimating Likelihood of Representations

Ouyang, Yuqi; Sánchez, Vı́ctor

doi:10.1109/icpr48806.2021.9412694

Cited by 14 publications

(25 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some tasks remain challenging however, such as video anomaly detection [3] as the events sought represent outliers that may occur infrequently, or not, over extended periods of monitoring. Recently proposed solutions such as building and managing a context graph [8], which could become memory intesive, posing the problem as a gaussian expectationmaximization issue [9], which increases computation, or tracking trajectories [10] are likely to cost resources. The expense will be compounded in a long running surveillance application, and is a motivator for this work.…”

Section: Supporting Workmentioning

confidence: 99%

Unsupervised Context Distillation from Weakly Supervised Data to Augment Video Question Answering

Gaynor

2023

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

Anomaly detection by tracking if the context of a video stream has changed could be useful, but supervised training to classify video context can be cumbersome and error prone. Instead, we apply a cascade of clustering techniques that operate on a weakly supervised video data lake to extract a context representation of a video sequence. We then train a bi-directional LSTM model to mimic the functionality of the cascade and predict a context representation from video. Additional experiments have shown that if the context is fed as an additional input to a legacy Video Question Answering solution, loss improves by more than 20% relative to it's baseline after training over 120 epochs, which is significant as current state of the art accuracy for VideoQA solutions is close to 50%. This report is also a demonstration of how to chart a path to freedom from the requirement to explicitly label data, while preserving semantics.

show abstract

Section: Supporting Workmentioning

confidence: 99%

Unsupervised Context Distillation from Weakly Supervised Data to Augment Video Question Answering

Gaynor

2023

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

show abstract

“…Experiments in this literature show the superiority of the model by introducing large-scale videos consisting of various real anomalies. Considering the advantages of traditional methods and deep learning methods in video anomaly detection, literature [24] combines the two and proposes a depth probability model for video anomaly detection. In this model, video anomaly detection is regarded as an unsupervised outlier detection task.…”

Section: Related Workmentioning

confidence: 99%

Multi Chunk Learning Based Auto Encoder for Video Anomaly Detection

Qi¹,

Ji²,

Zhang³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Video anomaly detection is essential to distinguish abnormal events in large volumes of surveillance video and can benefit many fields such as traffic management, public security and failure detection. However, traditional video anomaly detection methods are unable to accurately detect and locate abnormal events in real scenarios, while existing deep learning methods are likely to omit important information when extracting features. In order to avoid omitting important features and improve the accuracy of abnormal event detection and localization, this paper proposes a novel method called Multi Chunk Learning based Skip Connected Convolutional Auto Encoder (MCSCAE). The proposed method improves the accuracy of video anomaly detection by obtaining more vital information. In the data sorting phase, non-uniform chunking is proposed to divide the video frame into several chunks of different sizes to avoid obtaining unnecessary information and omitting crucial information. In order to well reflect the abnormal motion of objects in the video, a new feature, the inter frame flow feature, which is obtained by merging inter frame difference and optical flow features, is proposed to extract motion feature. Moreover, in this paper, skip connection in the auto encoder is utilized during the training phase to reduce the reconstruction error between the original frames and the reconstruction frames, so that the reconstruction error can be used to detect abnormal events during testing. Experience on three public datasets verifies the effectiveness and accuracy of our proposed method. Experimental results show that the proposed method can detect and locate abnormal events outperforms other recent methods significantly.

show abstract

“…In this type of approach, two ways are usually used to train a model. Either separately training the feature extraction and clustering steps [48,13,14,41,32], or jointly training both steps end-to-end [1,11,34,3,27,2]. Weakly-supervised models use a small number of abnormal frames with labels for training.…”

Section: Related Workmentioning

confidence: 99%

Look at Adjacent Frames: Video Anomaly Detection without Offline Training

Ouyang¹,

Shen²,

Sánchez³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a solution to detect anomalous events in videos without the need to train a model offline. Specifically, our solution is based on a randomly-initialized multilayer perceptron that is optimized online to reconstruct video frames, pixel-by-pixel, from their frequency information. Based on the information shifts between adjacent frames, an incremental learner is used to update parameters of the multilayer perceptron after observing each frame, thus allowing to detect anomalous events along the video stream. Traditional solutions that require no offline training are limited to operating on videos with only a few abnormal frames. Our solution breaks this limit and achieves strong performance on benchmark datasets.

show abstract

Video Anomaly Detection by Estimating Likelihood of Representations

Cited by 14 publications

References 32 publications

Unsupervised Context Distillation from Weakly Supervised Data to Augment Video Question Answering

Unsupervised Context Distillation from Weakly Supervised Data to Augment Video Question Answering

Multi Chunk Learning Based Auto Encoder for Video Anomaly Detection

Look at Adjacent Frames: Video Anomaly Detection without Offline Training

Contact Info

Product

Resources

About