Learning Normal Dynamics in Videos with Meta Prototype Network

Lv, Hui; Chen, Chen; Cui, Zhen; Xu, Chunyan; Li, Yong; Yang, Jian

doi:10.1109/cvpr46437.2021.01517

Cited by 135 publications

(63 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table I shows that the model trained for prediction performs comparably to state of the art results. Performance on UCSDPed1 is relatively poor, whilst for CUHK Avenue, the AUC is better than most methods, except FlowNet-Unet-GAN [14], MemAE [17], LMN [18], MPD [19]. However, MemAE [17], LMN [18] and MPD [19] have more parameters than our models which is shown in table III.…”

Section: B Anomalous Event Detectionmentioning

confidence: 81%

“…The score decreases when an anomaly (a running man) appears on the scene. learning methodology is introduced into a Dynamic Prototype Unit (DPU) to learn prototypes for encoding normal dynamics and to enable the fast adaption capacity to a new scene with only a few training frames [19]. As in previous work [18], the DPU inputs the encoding feature maps, which are outputs of the encoder part of U-net, to generate a pool of dynamic prototypes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM

Tran¹

2022

Preprint

View full text Add to dashboard Cite

In this paper, we propose a novel method for video anomaly detection motivated by an existing architecture for sequence-to-sequence prediction and reconstruction using a spatio-temporal convolutional Long Short-Term Memory (convL-STM). As in previous work on anomaly detection, anomalies arise as spatially localised failures in reconstruction or prediction. In experiments with five benchmark datasets, we show that using prediction gives superior performance to using reconstruction. We also compare performance with different length input/output sequences. Overall, our results using prediction are comparable with the state of the art on the benchmark datasets.

show abstract

Section: B Anomalous Event Detectionmentioning

confidence: 81%

Section: Introductionmentioning

confidence: 99%

Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM

Tran¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Table 1 shows that the model trained for prediction performs comparably to state of the art results. Performance on UCSDPed1 is relatively poor, whilst for CUHK Avenue, the AUC is better than most methods, except FlowNet-Unet-GAN [14], MemAE [17], LMN [18], MPD [19]. However, MemAE [17], LMN [18] and MPD [19] have more parameters than our models which is shown in Table 3.…”

Section: Anomalous Event Detectionmentioning

confidence: 83%

“…Performance on UCSDPed1 is relatively poor, whilst for CUHK Avenue, the AUC is better than most methods, except FlowNet-Unet-GAN [14], MemAE [17], LMN [18], MPD [19]. However, MemAE [17], LMN [18] and MPD [19] have more parameters than our models which is shown in Table 3. Table 2 shows the results when different models are used.…”

Section: Anomalous Event Detectionmentioning

confidence: 83%

“…However, it is impossible to find an optimal threshold to distinguish between normal and abnormal patterns under various scenarios. Meta-learning methodology is introduced into a Dynamic Prototype Unit (DPU) to learn prototypes for encoding normal dynamics and to enable the fast adaption capacity to a new scene with only a few training frames [19]. As in previous work [18], the DPU inputs the encoding feature maps, which are outputs of the encoder part of U-net, to generate a pool of dynamic prototypes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anomaly Detection Using Prediction Error with Spatio-Temporal Convolutional LSTM

Tran

Hogg

2022

UD-JST

View full text Add to dashboard Cite

In this paper, we propose a novel method for video anomaly detection motivated by an existing architecture for sequence-to-sequence prediction and reconstruction using a spatio-temporal convolutional Long Short-Term Memory (convLSTM). As in previous work on anomaly detection, anomalies arise as spatially localised failures in reconstruction or prediction. In experiments with five benchmark datasets, we show that using prediction gives superior performance to using reconstruction. We also compare performance with different length input/output sequences. Overall, our results using prediction are comparable with the state of the art on the benchmark datasets.

show abstract

Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection

Yang

Liu

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Learning Normal Dynamics in Videos with Meta Prototype Network

Cited by 135 publications

References 32 publications

Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM

Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM

Anomaly Detection Using Prediction Error with Spatio-Temporal Convolutional LSTM

Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection

Contact Info

Product

Resources

About