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
Improved human action recognition approach based on two-stream convolutional neural network model
TL;DR: Experimental results on KTH, Weizmann, UT-interaction, and TenthLab dataset showed that the proposed algorithm has higher accuracy than the other literature.
Journal ArticleDOI
Shadow Removal by a Lightness-Guided Network with Training on Unpaired Data
TL;DR: A new Lightness-Guided Shadow Removal Network (LG-ShadowNet) is presented, which first train a CNN module to compensate for the lightness and then train a second CNN module with the guidance of lightness information from the first CNN module for final shadow removal.
Journal ArticleDOI
Repetitive assembly action recognition based on object detection and pose estimation
TL;DR: The YOLOv3 algorithm is initially applied to locate and judge the assembly tools and recognize the worker's assembly action, and the pose estimation algorithm CPM based on deep learning is used to realize the recognition of human joint.
Proceedings ArticleDOI
Two-Stream Flow-Guided Convolutional Attention Networks for Action Recognition
An Tran,Loong-Fah Cheong +1 more
TL;DR: Crosslink layers from the temporal network to the spatial network are developed to guide the spatial-stream to pay more attention to the human foreground areas and be less affected by background clutter.
Journal ArticleDOI
Toward Efficient Action Recognition: Principal Backpropagation for Training Two-Stream Networks
TL;DR: It is proved that with the proposed selection strategies, performing the backpropagation on the selected subset is capable of decreasing the loss of the whole snippets as well, and the proposed PBNets are evaluated on two standard video action recognition benchmarks UCF101 and HMDB51.
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.