Filters








208 Hits in 6.9 sec

Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies [article]

Masoud Pourreza, Mohammadreza Salehi, Mohammad Sabokrou
2021 arXiv   pre-print
Video anomaly detection has proved to be a challenging task owing to its unsupervised training procedure and high spatio-temporal complexity existing in real-world scenarios.  ...  To address this issue, we propose a novel yet efficient method named Ano-Graph for learning and modeling the interaction of normal objects.  ...  STG Generation: spatio-temporal graph i.e. G st of a video with T frames is made by using the spatial G space t and the temporal G time t graphs for all timestamps t ∈ T .  ... 
arXiv:2103.10502v2 fatcat:g3uhxx7kgbgabdsyj5b76be6fm

A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos [article]

Xianlin Zeng, Yalong Jiang, Wenrui Ding, Hongguang Li, Yafeng Hao, Zifeng Qiu
2021 arXiv   pre-print
Deep learning models have been widely used for anomaly detection in surveillance videos.  ...  In this paper, we propose a Hierarchical Spatio-Temporal Graph Convolutional Neural Network (HSTGCNN) to address these problems, the HSTGCNN is composed of multiple branches that correspond to different  ...  We name it Hierarchical Spatial-Temporal Graph Convolutional Neural Network (HSTGCNN).  ... 
arXiv:2112.04294v2 fatcat:vi26nkpf2jhc7b2sjseo4b4rii

A Self-Attention Augmented Graph Convolutional Clustering Networks for Skeleton-Based Video Anomaly Behavior Detection

Chengming Liu, Ronghua Fu, Yinghao Li, Yufei Gao, Lei Shi, Weiwei Li
2021 Applied Sciences  
As far as we know, we are the first group to utilize self-attention for video anomaly detection tasks by enhancing spatial temporal graph convolution.  ...  In this paper, we propose a new method for detecting abnormal human behavior based on skeleton features using self-attention augment graph convolution.  ...  Conclusions In this work, we propose a novel spatial temporal self-attention augmented graph convolutional clustering networks for skeleton-based video anomaly detection tasks by employing the SAA-STGCAE  ... 
doi:10.3390/app12010004 fatcat:2cufica45rapfluo74b4563ezu

Graph Embedded Pose Clustering for Anomaly Detection [article]

Amir Markovitz, Gilad Sharir, Itamar Friedman, Lihi Zelnik-Manor, Shai Avidan
2020 arXiv   pre-print
We propose a new method for anomaly detection of human actions. Our method works directly on human pose graphs that can be computed from an input video sequence.  ...  The second is a coarse-grained anomaly detection data set (e.g., a Kinetics-based data set) where few actions are considered normal, and every other action should be considered abnormal.  ...  We propose a deep temporal graph autoencoder based architecture for embedding the temporal pose graphs.  ... 
arXiv:1912.11850v2 fatcat:ok7ida67bjelnls2nftqp5ppoi

Weakly Supervised Graph Convolutional Neural Network for Human Action Localization

Daisuke Miki, Shi Chen, Kazuyuki Demachi
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
To address this problem, we propose a skeleton-based human action recognition and localization method using weakly supervised graph convolutional neural networks, which are both spatially and temporally  ...  Skeleton-based human action recognition from video sequences is currently an active topic of research.  ...  Acknowledgments This work was supported by Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research Grant Numbers JP19K20310.  ... 
doi:10.1109/wacv45572.2020.9093551 dblp:conf/wacv/MikiCD20 fatcat:vj67gbtwnbcq5jquxrxlaaixyi

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future [article]

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 arXiv   pre-print
As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interactive nodes connected by edges whose weights can be  ...  either temporal associations or anatomical junctions.  ...  Temporal convolutional networks (TCNs) are used on top of normal convolutional networks to capture temporal features.  ... 
arXiv:2105.13137v1 fatcat:gm7d2ziagba7bj3g34u4t3k43y

Deep social force network for anomaly event detection

Xingming Yang, Zhiming Wang, Kewei Wu, Zhao Xie, Jinkui Hou
2021 IET Image Processing  
Anomaly event detection is vital in surveillance video analysis. However, how to learn the discriminative motion in the crowd scene is still not tackled.  ...  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.  ...  The aggregation model [20] , spatial and temporal constrained frame prediction [23] , temporally coherent sparse coding RNN [23] , stacked RNN auto-encoder [24] , skeleton GRU [13] , skeleton graph  ... 
doi:10.1049/ipr2.12299 fatcat:swdktlrbtnad5dwib35v3sq7s4

Spectral Graph Skeletons for 3D Action Recognition [chapter]

Tommi Kerola, Nakamasa Inoue, Koichi Shinoda
2015 Lecture Notes in Computer Science  
We present spectral graph skeletons (SGS), a novel graphbased method for action recognition from depth cameras.  ...  The contribution of this paper is to leverage a spectral graph wavelet transform (SGWT) for creating an overcomplete representation of an action signal lying on a 3D skeleton graph.  ...  The first author acknowledges the Japanese Government (Monbukagakusho:MEXT) scholarship support for carrying out this research.  ... 
doi:10.1007/978-3-319-16817-3_27 fatcat:fnif5znejnhjboi2or77gzbezy

2021 16TH IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)

2021 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)  
Masked Batch Normalization to Improve Tracking-Based Sign Language Recognition Using Graph Convolutional Networks Natsuki Takayama; Gibran Benitez-Garcia; Hiroki Takahashi 31.  ...  Exploiting Emotional Dependencies with Graph Convolutional Networks for Facial Expression Recognition Panagiotis Antoniadis; Panagiotis P Filntisis; Petros Maragos 47.  ... 
doi:10.1109/fg52635.2021.9667043 fatcat:q67llypbybbrbacdiyia6hs2pe

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TMM 2021 1442-1453 Spatial-Temporal Cascade Autoencoder for Video Anomaly Detection in Crowded Scenes.  ...  ., +, TMM 2021 1367-1382 Spatial-Temporal Cascade Autoencoder for Video Anomaly Detection in Crowded Scenes.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

Cross-view human action recognition from depth maps using spectral graph sequences

Tommi Kerola, Nakamasa Inoue, Koichi Shinoda
2017 Computer Vision and Image Understanding  
We evaluate two view-invariant graph types: skeleton-based and keypoint-based.  ...  The skeleton-based descriptor captures the spatial pose of the subject, whereas the keypoint-based is able to capture complementary information about human-object interaction and the shape of the point  ...  Acknowledgments We thank the anonymous reviewers for their insightful comments, which helped improve the content of the paper.  ... 
doi:10.1016/j.cviu.2016.10.004 fatcat:d55ao2jgwvaw5eroyou5r2a7ee

Dual Discriminator Generative Adversarial Network for Video Anomaly Detection

Fei Dong, Yu Zhang, Xiushan Nie
2020 IEEE Access  
Because of the rarity of abnormal events and the complicated characteristic of videos, video anomaly detection is challenging and has been studied for a long time.  ...  Video anomaly detection is an essential task because of its numerous applications in various areas.  ...  For video anomaly detection, spatial and temporal information are both important. To predict future frames better, we consider both appearance and motion constraints.  ... 
doi:10.1109/access.2020.2993373 fatcat:y7qrrnapcnbp3agngpwkr5csp4

Multi Chunk Learning Based Auto Encoder for Video Anomaly Detection

Xiaosha Qi, Genlin Ji, Jie Zhang, Bo Sheng
2022 Intelligent Automation and Soft Computing  
The proposed method improves the accuracy of video anomaly detection by obtaining more vital information.  ...  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.  ...  [22] propose a prediction network based on spatial temporal graph convolutional networks for skeleton-based video anomaly detection.  ... 
doi:10.32604/iasc.2022.027182 fatcat:t4mi4uqepngi5oqkgdvqsujose

Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition [article]

Xiangbo Shu, Jiawen Yang, Rui Yan, Yan Song
2022 arXiv   pre-print
Thus, we attempt to effectively aggregate the discriminative information of actions and interactions from both RGB videos and skeleton sequences by attentively fusing multi-modal features.  ...  (ESE) attentions for attentively fusing the multi-modal features in the modal and channel-wise ways.  ...  For example, Yan et al. [11] proposed a Spatial-Temporal Graph Convolutional Network (ST-GAN) that employs graph convolution to aggregate the joint features in the spatial dimension. Liu et al.  ... 
arXiv:2112.10992v2 fatcat:ersbt5s7r5f5teurcormauwuxa

Intelligent video surveillance: a review through deep learning techniques for crowd analysis

G. Sreenu, M. A. Saleem Durai
2019 Journal of Big Data  
Majority of the papers reviewed in this survey are based on deep learning technique. Various deep learning methods are compared in terms of their algorithms and models.  ...  Among them violence detection is difficult to handle since it involves group activity.  ...  Spatial temporal convolutional neural networks for anomaly detection and localization in crowded scenes [114] shows the problem related with crowd analysis is challenging because of the following reasons  ... 
doi:10.1186/s40537-019-0212-5 fatcat:mh7d5d5c5zeczf5sdmgwz3claq
« Previous Showing results 1 — 15 out of 208 results