Open AccessPosted Content
Convolutional Two-Stream Network Fusion for Video Action Recognition
TLDR
In this paper, a spatial and temporal network can be fused at the last convolution layer without loss of performance, but with a substantial saving in parameters, and furthermore, pooling of abstract convolutional features over spatiotemporal neighbourhoods further boosts performance.Abstract:
Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet towers both spatially and temporally in order to best take advantage of this spatio-temporal information. We make the following findings: (i) that rather than fusing at the softmax layer, a spatial and temporal network can be fused at a convolution layer without loss of performance, but with a substantial saving in parameters; (ii) that it is better to fuse such networks spatially at the last convolutional layer than earlier, and that additionally fusing at the class prediction layer can boost accuracy; finally (iii) that pooling of abstract convolutional features over spatiotemporal neighbourhoods further boosts performance. Based on these studies we propose a new ConvNet architecture for spatiotemporal fusion of video snippets, and evaluate its performance on standard benchmarks where this architecture achieves state-of-the-art results.read more
Citations
More filters
Journal ArticleDOI
UCF-STAR: A Large Scale Still Image Dataset for Understanding Human Actions
TL;DR: A novel approach relying on predicting temporal information is presented, yielding higher accuracy on 5 widely-used datasets, and the role of “latent” motion information in recognizing human actions in still images is shown.
Posted Content
Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
TL;DR: Parallel Separable 3D Convolution (PmSCn) as mentioned in this paper applies m parallel streams of n 2D and one 1D convolution layers along different dimensions.
Patent
Human body behavior recognition method and device based on residual error network
TL;DR: In this article, a human body behavior recognition method and device based on a residual error network is proposed, which consists of the steps: converting a video into an RGB image and an optical flow image through opencv, extracting the spatial feature and time feature through a residual errors network, carrying out the fusion of two features, inputting the features into a classifier for classification, and determining the class of a behavior of a person in the video.
Journal ArticleDOI
Human action recognition in videos with articulated pose information by deep networks
TL;DR: This paper proposes a way to cope with low-level actions by combining information of human body joints to aid action recognition by using high-level features computed by a convolutional neural network which was pre-trained on Imagenet, with articulated body joints as low- level features.
Book ChapterDOI
Two-Stream CNN Architecture for Anomalous Event Detection in Real World Scenarios
TL;DR: A database pre-processing algorithm has been proposed to capture the spatial and temporal frames in every second, which is subsequently utilized in two-stream 2D-CNN architecture for feature extraction and classification.
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.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.