Spatio-Temporal AutoEncoder for Video Anomaly Detection

By Yiru Zhao, Bing Deng, Chen Shen, Yao Liu, Hongtao Lu, Xiansheng Hua. ACM Multimedia, 2017

552 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fef6f1e04fa64f2f26ac9f01cd143dd19e549790

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Amir Atapour-Abarghouei
2. Toby P. Breckon
3. Samet Akcay
4. Truyen Tran
5. Svetha Venkatesh
6. Jianfeng Feng
7. Vuong Le
8. Jongyoun Noh

In Computer Networks and Communications

1. Jianfeng Feng
2. Svetha Venkatesh
3. Jongyoun Noh
4. Toby P. Breckon
5. Hyunjong Park
6. Dilip Ravi Kiran
7. Mathew Thomas
8. Amir Atapour-Abarghouei

In Computer Vision and Pattern Recognition

1. In-So Kweon
2. Xiaogang Wang
3. Toby P. Breckon
4. Dahun Kim
5. Amir Atapour-Abarghouei
6. Luc Van Gool
7. Samet Akcay
8. Weishi Zheng

Citations in the corpus

• A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction (2021, methodology): “Rather than traditional handcrafted feature based methods [1, 20, 2, 34], a lot of modern deep neural network based methods [11, 45, 50, 31, 25, 30, 8, 36, 38, 47, 43, 24] have been proposed for VAD.”
• Learning Memory-Guided Normality for Anomaly Detection (2020, background): “It also uses CNN features but us-ing a 3D Conv-AE to retrieve relevant memory items that record normal patterns, where the items are updated during training only.”
• Sub-Image Anomaly Detection with Deep Pyramid Correspondences (2020, unknown): “TSC [23] StackRNN [23] AE-Conv3D [35] MemAE [12] AE(2D) [16] ITAE [19] SPADE”
• MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection (2021, methodology): “Unsupervised learning methods [9, 29, 7, 30, 15, 13, 32, 5] encode the usual pattern with only normal training samples and then detect the distinctive encoded patterns as anomalies.”
• An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos (2018, methodology): “Authors in [61] propose to use a 3D kernel by stacking T-frames together as in [41].”
• Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles (2018, methodology): “To our best knowledge, only few works (Zhao et al. 2017; Vondrick, Pirsiavash, and Torralba 2016) exploit the 3D architectures in self-supervised feature learning.”
• GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training (2018, background): “Much of the recent work on this problem domain pays particular attention to the use of spatiotemporal features by modeling spatiotemporal CNN [22], 3D convolutional autoencoders [23, 24] and long short-term memories [25].”
• Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos (2019, methodology): “Some of these methods include Convolutional autoencoder [13], spatio-temporal autoencoder [5], 3D Convnet AE [27], and Temporally-coherent Sparse Coding StackedRNN [20].”
• Visual Memorability for Robotic Interestingness via Unsupervised Online Learning (2020, background): “proposed a spatio-temporal autoencoder to extract both spatial and temporal features for anomaly detection [42].”