Graph Embedded Pose Clustering for Anomaly Detection

Markovitz, Amir; Sharir, Gilad; Friedman, Itamar; Zelnik-Manor, Lihi; Avidan, Shai

doi:10.1109/cvpr42600.2020.01055

Cited by 157 publications

(102 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even under the harsh conditions, we have achieved a definite improvement compared with other methods. Our AUC value is 92.1% and the EER value is 13.4%, which also outperforms the state‐of‐the art methods 32–34 . Overall, the test shows that the desired results are achieved.…”

Section: Resultsmentioning

confidence: 62%

See 1 more Smart Citation

Positive unlabeled learning‐based anomaly detection in videos

Sun

Yuan

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

Anomaly detection plays a critical role in intelligent video surveillance. However, real‐world video data obtained always contains large numbers of normal video data, along with large numbers of unlabeled data. A promising solution with one‐class classification and semi‐supervised learning may not be satisfactory as they fail to make good use of unlabeled data with only normal data available. In this paper, we introduced a new framework, called Positive Unlabeled learning‐based Anomaly event Detection (PU‐AD), to exploit the weakly‐supervised information. To the best of our knowledge, this is the first work that introduces the PU idea and achieves detecting abnormal events with a limited number of partially labeled data. Experiments on real‐world surveillance videos show that the proposed method outperforms the existing state‐of‐the‐art methods.

show abstract

Section: Resultsmentioning

confidence: 62%

“…Figure 8 are the ROC curve between the proposed method and the other four methods. As ShanghaiTech is a new data set for abnormal event detection, there are only a few recent studies 14,32–34 reporting results on it. Comparing with these latest algorithms, the CGDL 14 method seems to be a slightly better preference in terms of EER.…”

Section: Resultsmentioning

confidence: 99%

Positive unlabeled learning‐based anomaly detection in videos

Sun

Yuan

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

show abstract

“…8, our poseguided strategy consistently outperforms the random one in terms of accuracy and training efficiency. The Graph Embedded Pose Clustering (GEPC) method [Markovitz et al, 2020] performs sililar to our strategy. Besides, it can be seen from Fig.…”

Section: Discussionmentioning

confidence: 99%

Few-shot Neural Human Performance Rendering from Sparse RGBD Videos

Pang

Chen

Luo

et al. 2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Recent neural rendering approaches for human activities achieve remarkable view synthesis results, but still rely on dense input views or dense training with all the capture frames, leading to deployment difficulty and inefficient training overload. However, existing advances will be ill-posed if the input is both spatially and temporally sparse. To fill this gap, in this paper we propose a few-shot neural human rendering approach (FNHR) from only sparse RGBD inputs, which exploits the temporal and spatial redundancy to generate photo-realistic free-view output of human activities. Our FNHR is trained only on the key-frames which expand the motion manifold in the input sequences. We introduce a two-branch neural blending to combine the neural point render and classical graphics texturing pipeline, which integrates reliable observations over sparse key-frames. Furthermore, we adopt a patch-based adversarial training process to make use of the local redundancy and avoids over-fitting to the key-frames, which generates fine-detailed rendering results. Extensive experiments demonstrate the effectiveness of our approach to generate high-quality free view-point results for challenging human performances under the sparse setting.

show abstract

“…By changing the threshold gradually, we can arrive at a ROC curve. The above methods learn normal feature pattern [23,24], normal frame prediction [21,26], and normal skeleton pattern [13,14]. As abnormal video has not been seen in training, therefore, the unsupervised methods get lower performance than the supervised methods.…”

Section: Comparison With Unsupervised Methodsmentioning

confidence: 99%

Deep social force network for anomaly event detection

Yang

Wang

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Anomaly event detection is vital in surveillance video analysis. However, how to learn the discriminative motion in the crowd scene is still not tackled. Here, a deep social force network by exploiting both social force extracting and deep motion coding is proposed. Given a grid of particles with velocity provided by the optical flow, the interaction force in the crowd scene is investigated and a social force module is embedded in a deep network. A deep motion convolution was further designed with a 3D (DMC-3D) module. The DMC-3D not only eliminates the noise motion in the crowd scene with a spatial encoder-decoder but also learns the 3D feature with a spatio-temporal encoder. The deep social force coding is modelled with multiple features, in which each feature can describe specific anomaly motion. The experiments on UCF-Crime and ShanghaiTech datasets demonstrate that our method can predict the temporal localization of anomaly events and outperform the stateof-the-art methods.

show abstract

Graph Embedded Pose Clustering for Anomaly Detection

Cited by 157 publications

References 17 publications

Positive unlabeled learning‐based anomaly detection in videos

Positive unlabeled learning‐based anomaly detection in videos

Few-shot Neural Human Performance Rendering from Sparse RGBD Videos

Deep social force network for anomaly event detection

Contact Info

Product

Resources

About