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
Posted Content
TSM: Temporal Shift Module for Efficient Video Understanding
Ji Lin,Chuang Gan,Song Han +2 more
TL;DR: A generic and effective Temporal Shift Module (TSM) that can achieve the performance of 3D CNN but maintain 2D CNN’s complexity and is extended to online setting, which enables real-time low-latency online video recognition and video object detection.
Posted Content
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
TL;DR: It is shown that it is possible to replace many of the 3D convolutions by low-cost 2D convolution, suggesting that temporal representation learning on high-level “semantic” features is more useful.
Posted Content
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
Zhaofan Qiu,Ting Yao,Tao Mei +2 more
TL;DR: P3D ResNet as discussed by the authors proposes a pseudo-3D residual network to exploit all the variants of blocks but composes each in different placement of ResNet, following the philosophy that enhancing structural diversity with going deep could improve the power of neural networks.
Proceedings ArticleDOI
Lip Reading Sentences in the Wild
TL;DR: The WLAS model trained on the LRS dataset surpasses the performance of all previous work on standard lip reading benchmark datasets, often by a significant margin, and it is demonstrated that if audio is available, then visual information helps to improve speech recognition performance.
Proceedings ArticleDOI
Spatiotemporal Multiplier Networks for Video Action Recognition
TL;DR: A general ConvNet architecture for video action recognition based on multiplicative interactions of spacetime features that combines the appearance and motion pathways of a two-stream architecture by motion gating and is trained end-to-end.
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.