Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection
Mahdyar Ravanbakhsh,Moin Nabi,Hossein Mousavi,Enver Sangineto,Nicu Sebe +4 more
- pp 1689-1698
TLDR
In this article, the authors proposed to measure local abnormality by combining semantic information (inherited from existing CNN models) with low-level optical flow, which can be used without the fine-tuning phase.Abstract:
Most of the crowd abnormal event detection methods rely on complex hand-crafted features to represent the crowd motion and appearance. Convolutional Neural Networks (CNN) have shown to be a powerful instrument with excellent representational capacities, which can leverage the need for hand-crafted features. In this paper, we show that keeping track of the changes in the CNN feature across time can be used to effectively detect local anomalies. Specifically, we propose to measure local abnormality by combining semantic information (inherited from existing CNN models) with low-level optical-flow. One of the advantages of this method is that it can be used without the fine-tuning phase. The proposed method is validated on challenging abnormality detection datasets and the results show the superiority of our approach compared with the state-of-theart methods.read more
Citations
More filters
Proceedings ArticleDOI
Abnormal event detection in videos using generative adversarial nets
TL;DR: In this paper, the authors use GANs to learn an internal representation of the scene normality and then compare the real data with both the appearance and motion representations reconstructed by the GAN and abnormal areas are detected by computing local differences.
Proceedings ArticleDOI
Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection
TL;DR: A graph convolutional network is devised that propagates supervisory signals from high-confidence snippets to low-confidence ones and is capable of providing cleaned supervision for action classifiers.
Proceedings ArticleDOI
Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video
TL;DR: An unsupervised feature learning framework based on object-centric convolutional auto-encoders to encode both motion and appearance information is introduced and a supervised classification approach based on clustering the training samples into normality clusters is proposed.
Proceedings ArticleDOI
Training Adversarial Discriminators for Cross-Channel Abnormal Event Detection in Crowds
TL;DR: Generative Adversarial Nets (GANs), which are trained to generate only the normal distribution of the data, are proposed, which outperforms previous state-of-the-art methods in both the frame-level and the pixel-level evaluation.
Posted Content
Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video
TL;DR: Zhang et al. as mentioned in this paper proposed an unsupervised feature learning framework based on object-centric convolutional auto-encoders to encode both motion and appearance information.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Posted Content
Fully Convolutional Networks for Semantic Segmentation
TL;DR: It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.
Posted Content
CNN Features off-the-shelf: an Astounding Baseline for Recognition
TL;DR: A series of experiments conducted for different recognition tasks using the publicly available code and model of the OverFeat network which was trained to perform object classification on ILSVRC13 suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.