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
Dynamic gesture recognition by using CNNs and star RGB: A temporal information condensation
TL;DR: This work proposes a technique capable of condensing a dynamic gesture, shown in a video, in just one RGB image, and calls it star RGB, which reaches the state-of-the-art when considering this dataset and only color information.
Posted Content
Action Recognition with Spatio-Temporal Visual Attention on Skeleton Image Sequences
TL;DR: Wang et al. as mentioned in this paper proposed a two-branch attention architecture that focuses on spatio-temporal key stages and filters out unreliable joint predictions, which achieved state-of-the-art performance.
Journal ArticleDOI
Automatic segmentation of bone surfaces from ultrasound using a filter-layer-guided CNN
TL;DR: The proposed convolutional neural network-based technique for segmentation of bone surfaces from in vivo US scans utilizes fusion of feature maps and employs multi-modal images to abate sensitivity to variations caused by imaging artifacts and low intensity bone boundaries.
Posted Content
Video-based Person Re-identification with Accumulative Motion Context
TL;DR: The experimental results demonstrate that the proposed AMOC network outperforms state-of-the-arts for video-based re-identification significantly and confirm the advantage of exploiting long-range motion context forVideo-based person re-Identification, validating the motivation evidently.
Posted Content
What have we learned from deep representations for action recognition
TL;DR: In this paper, the authors show that cross-stream fusion enables the learning of true spatiotemporal features rather than simply separate appearance and motion features for recognizing human actions, and the networks can learn local representations that are highly class specific, but also generic representations that can serve a range of classes.
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.