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
Proceedings ArticleDOI
Skeleton-Based Action Recognition of People Handling Objects
TL;DR: A new framework for recognizing object-related human actions by graph convolutional networks using human and object poses is proposed, which outperforms the state-of-the-art method for skeleton-based action recognition.
Proceedings ArticleDOI
Two-Stream Convolution Neural Network with Video-stream for Action Recognition
TL;DR: A new ConvNet architecture called CVDN(Combined Video-stream Deep Network) is proposed to extract more spatio-temporal features from video fragments so as to effectively utilize the temporal information in the dataset.
Posted Content
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations
TL;DR: In this paper, the authors used 3D hand pose annotations to recognize first-person dynamic hand actions interacting with 3D objects, using RGB-D video sequences comprised of more than 100K frames of 45 daily hand action categories, involving 26 different objects in several hand configurations.
Journal ArticleDOI
Global motion estimation with iterative optimization-based independent univariate model for action recognition
TL;DR: An iterative optimization scheme for GM estimation which removes the outlier points step by step and estimates global motions in a coarse-to-fine manner and the LM is estimated through a Spatio-temporal threshold-based method.
Journal ArticleDOI
Movement Estimation Using Soft Sensors Based on Bi-LSTM and Two-Layer LSTM for Human Motion Capture
Haitao Guo,Yunsick Sung +1 more
TL;DR: A framework to estimate single-arm orientations using soft sensors mainly by combining a Bi-long short-term memory (Bi-LSTM) and two-layer LSTM and the contextual features of consecutive sensory arm movements are analyzed, which provides an efficient way to improve the accuracy of arm movement estimation.
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.