Parallelizing Convolutional Neural Networks for Action Event Recognition in Surveillance Videos

Wang, Qicong; Zhao, Jinhao; Gong, Dingxi; Shen, Yehu; Li, Maozhen; Lei, Yunqi

doi:10.1007/s10766-016-0451-4

Cited by 9 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In convolutional neural network, convolution is mainly performed for generating feature maps, which only contain spatial information. For video analysis, we need to extract temporal motion information from multiple successive video frames . Therefore, the convolution phase of convolutional neural network should perform spatial and temporal convolution simultaneously and get spatio‐temporal features.…”

Section: D Convolution and Spatio‐temporal Convolutionmentioning

confidence: 99%

Temporal sparse feature auto‐combination deep network for video action recognition

Wang

Gong

et al. 2018

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary In order to deal with action recognition for large‐scale video data, we present a spatio‐temporal auto‐combination deep network, which is able to extract deep features from short video segments by making full use of temporal contextual correlation of corresponding pixels among successive video frames. Based on conventional sparse encoding, we further consider the representative features in adjacent nodes of the hidden layers according to activation states similarities. A sparse auto‐combination strategy is applied to multiple input maps in each convolution stage. An information constraint of the representative features of hidden layer nodes is imposed to handle the adaptive sparse encoding of the topology. As a result, the learned features can represent the spatio‐temporal transition relationships better and the number of hidden nodes can be restricted to a certain range. We conduct a series of experiments on two public data sets. The experimental results show that our approach is more effective and robust in video action recognition compared with traditional methods.

show abstract

Section: D Convolution and Spatio‐temporal Convolutionmentioning

confidence: 99%

Temporal sparse feature auto‐combination deep network for video action recognition

Wang

Gong

et al. 2018

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…When faced with the massive data of terabyte or petabyte, MapReduce is used to solve the problem. Convolutional neural network based on MapReduce parallel [35,36] can also achieve a better result, but with the increasing of the number of parameters in the network model, and the difficulty of model training are increased as well. MapReduce is not suitable for high computing density iterative algorithm.…”

Section: Related Workmentioning

confidence: 99%

A Parallel Strategy for Convolutional Neural Network Based on Heterogeneous Cluster for Mobile Information System

Zhang¹,

Xiao²,

Wan³

et al. 2017

Mobile Information Systems

View full text Add to dashboard Cite

With the development of the mobile systems, we gain a lot of benefits and convenience by leveraging mobile devices; at the same time, the information gathered by smartphones, such as location and environment, is also valuable for business to provide more intelligent services for customers. More and more machine learning methods have been used in the field of mobile information systems to study user behavior and classify usage patterns, especially convolutional neural network. With the increasing of model training parameters and data scale, the traditional single machine training method cannot meet the requirements of time complexity in practical application scenarios. The current training framework often uses simple data parallel or model parallel method to speed up the training process, which is why heterogeneous computing resources have not been fully utilized. To solve these problems, our paper proposes a delay synchronization convolutional neural network parallel strategy, which leverages the heterogeneous system. The strategy is based on both synchronous parallel and asynchronous parallel approaches; the model training process can reduce the dependence on the heterogeneous architecture in the premise of ensuring the model convergence, so the convolution neural network framework is more adaptive to different heterogeneous system environments. The experimental results show that the proposed delay synchronization strategy can achieve at least three times the speedup compared to the traditional data parallelism.

show abstract

“…Wang et. al [26] used MapReduce on Hadoop platform to take advantage of the computing power of multi core CPU to solve matrix parallel computation. However, the number of multi core CPU is far less than GPU can provide.…”

Section: Mapreduce In Cnnmentioning

confidence: 99%

“…Further researches introduced MapReduce paradigm to speed up various machine learning algorithms, i.e., locally weighted linear regression (LWLR), k-means, logistic regression (LR), naive Bayes (NB), support vector machine (SVM), gaussian discriminant analysis (GDA), expectation-maximization (EM) and backpropagation (NN) [24], stochastic gradient descent (SGD) [29], convolutional neural network (CNN) [26], extreme learning machine (ELM) [27].…”

Section: Introductionmentioning

confidence: 99%

Distributed Averaging CNN-ELM for Big Data

Budiman,

Fanany,

Basaruddin

2016

Preprint

View full text Add to dashboard Cite

Increasing the scalability of machine learning to handle big volume of data is a challenging task. The scale up approach has some limitations. In this paper, we proposed a scale out approach for CNN-ELM based on MapReduce on classifier level. Map process is the CNN-ELM training for certain partition of data. It involves many CNN-ELM models that can be trained asynchronously. Reduce process is the averaging of all CNN-ELM weights as final training result. This approach can save a lot of training time than single CNN-ELM models trained alone. This approach also increased the scalability of machine learning by combining scale out and scale up approaches. We verified our method in extended MNIST data set and not-MNIST data set experiment. However, it has some drawbacks by additional iteration learning parameters that need to be carefully taken and training data distribution that need to be carefully selected. Further researches to use more complex image data set are required.

show abstract

Parallelizing Convolutional Neural Networks for Action Event Recognition in Surveillance Videos

Cited by 9 publications

References 22 publications

Temporal sparse feature auto‐combination deep network for video action recognition

Temporal sparse feature auto‐combination deep network for video action recognition

A Parallel Strategy for Convolutional Neural Network Based on Heterogeneous Cluster for Mobile Information System

Distributed Averaging CNN-ELM for Big Data

Contact Info

Product

Resources

About