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
A Deep Learning based Approach for Precise Video Tagging
Sadia Ilyas,Hafeez Ur Rehman +1 more
TL;DR: A novel approach that integrates the video scene ontology with CNN (Convolutional Neural Network) for improved video tagging is proposed that captures the content of a video by extracting the information from individual key frames.
Journal ArticleDOI
Global2Salient: Self-adaptive feature aggregation for remote sensing smoke detection
TL;DR: A self-adaptive feature aggregation (SAFA) network is designed to distinguish smoke from other scenes in RS images to achieve the new state-of-the-art classification accuracy of 96.22% on USTC_SmokeRS data.
Posted Content
Video Action Understanding: A Tutorial.
TL;DR: This tutorial clarifies a taxonomy of video action problems, highlights datasets and metrics used to baseline each problem, describes common data preparation methods, and presents the building blocks of state-of-the-art deep learning model architectures.
Journal ArticleDOI
Multi-Scale Based Context-Aware Net for Action Detection
TL;DR: A novel multiple scales based context-aware net (MSCA-Net) is presented to effectively classify the action proposals for action detection in this paper and extensive experiments demonstrate the effectiveness of the designed structure.
Proceedings ArticleDOI
Human Action Recognition in Video Using DB-LSTM and ResNet
TL;DR: This study proposes a novel human action recognition method using convolutional neural networks (CNN) and deep bidirectional LSTM (DB-LSTM) networks, using only raw video frames, and evaluation results show a considerable increase in the efficiency of action recognition on the UCF 101 dataset.
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.