MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection

Feng, Jia-Chang; Hong, Fa-Ting; Zheng, Wei‐Shi

doi:10.1109/cvpr46437.2021.01379

Cited by 211 publications

(85 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sultani et al [22] propose the MIL framework using only video-level labels and introduce the large-scale anomaly detection dataset, UCF-Crime. This work inspires quite a few follow-up studies [28], [17], [4], [14], [26], [25], [6], [23], [26]. .…”

Section: General Anomaly Detectionmentioning

confidence: 80%

Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition

Tan¹,

Liu²

2022

Preprint

View full text Add to dashboard Cite

Detection of fights is an important surveillance application in videos. Most existing methods use supervised binary action recognition. Since frame-level annotations are very hard to get for anomaly detection, weakly supervised learning using multiple instance learning is widely used. This paper explores the detection of fights in videos as one special type of anomaly detection and as binary action recognition. We use the UBI-Fight and NTU-CCTV-Fight datasets for most of the study since they have frame-level annotations. We find that the anomaly detection has similar or even better performance than the action recognition. Furthermore, we study to use anomaly detection as a toolbox to generate training datasets for action recognition in an iterative way conditioned on the performance of the anomaly detection. Experiment results should show that we achieve state-ofthe-art performance on three fight detection datasets.

show abstract

Section: General Anomaly Detectionmentioning

confidence: 80%

Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition

Tan¹,

Liu²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Furthermore, the proposed approach does not optimize the feature space with any additional supervision. Some approaches such as Geogescu et al [9] and Feng et al [7] use additional supervision with pseudo labels to improve the latent features, enhancing accuracy of anomaly detection. On the other hand, our approach learns an accurate fusion of temporal and spatial scores without modifying the underlying feature space through additional supervision.…”

Section: Quantitative Resultsmentioning

confidence: 99%

Temporal Cues from Socially Unacceptable Trajectories for Anomaly Detection

Madan

Farkhondeh

Nasrollahi

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

State-of-the-Art (SoTA) deep learning-based approaches to detect anomalies in surveillance videos utilize limited temporal information, including basic information from motion, e.g., optical flow computed between consecutive frames. In this paper, we compliment the SoTA methods by including long-range dependencies from trajectories for anomaly detection. To achieve that, we first created trajectories by running a tracker on two SoTA datasets, namely Avenue and Shanghai-Tech. We propose a prediction-based anomaly detection method using trajectories based on Social GANs, also called in this paper as temporal-based anomaly detection. Then, we hypothesize that late fusion of the result of this temporal-based anomaly detection system with spatial-based anomaly detection systems produces SoTA results. We verify this hypothesis on two spatial-based anomaly detection systems. We show that both cases produce results better than baseline spatial-based systems, indicating the usefulness of the temporal information coming from the trajectories for anomaly detection. We observe that the proposed approach depicts the maximum improvement in micro-level Area-Under-the-Curve (AUC) by 4.1% on CUHK Avenue and 3.4% on Shanghai-Tech over one of the baseline method. We also show a high performance on cross-data evaluation, where we learn the weights to combine spatial and temporal information on Shanghai-Tech and perform evaluation on CUHK Avenue and vice-versa.

show abstract

“…While outlier exposure assumes labeled anomalies, our work aims at exploiting unlabeled anomalies in the training data. Notably, Pang et al (2020) have used an iterative scheme to detect abnormal frames in video clips, and Feng et al (2021) extend it to supervised video anomaly detection. Our work is more general and provides a principled way to improve the training strategy of all approaches mentioned in the paragraph "deep anomaly detection" when the training data is likely contaminated.…”

Section: Deep Anomaly Detectionmentioning

confidence: 99%

Latent Outlier Exposure for Anomaly Detection with Contaminated Data

Qiu¹,

Li²,

Kloft³

et al. 2022

Preprint

View full text Add to dashboard Cite

Anomaly detection aims at identifying data points that show systematic deviations from the majority of data in an unlabeled dataset. A common assumption is that clean training data (free of anomalies) is available, which is often violated in practice. We propose a strategy for training an anomaly detector in the presence of unlabeled anomalies that is compatible with a broad class of models. The idea is to jointly infer binary labels to each datum (normal vs. anomalous) while updating the model parameters. Inspired by outlier exposure (Hendrycks et al., 2018) that considers synthetically created, labeled anomalies, we thereby use a combination of two losses that share parameters: one for the normal and one for the anomalous data. We then iteratively proceed with block coordinate updates on the parameters and the most likely (latent) labels. Our experiments with several backbone models on three image datasets, 30 tabular data sets, and a video anomaly detection benchmark showed consistent and significant improvements over the baselines.

show abstract

MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection

Cited by 211 publications

References 27 publications

Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition

Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition

Temporal Cues from Socially Unacceptable Trajectories for Anomaly Detection

Latent Outlier Exposure for Anomaly Detection with Contaminated Data

Contact Info

Product

Resources

About