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
Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
TL;DR: In this paper, a local feature integration framework based on attention clusters was proposed, and a shifting operation was introduced to capture more diverse signals for video classification, achieving state-of-the-art performance on the ActivityNet Kinetics Challenge 2017 dataset.
Posted Content
Multi-style Generative Network for Real-time Transfer
Hang Zhang,Kristin J. Dana +1 more
TL;DR: In this article, a CoMatch layer was introduced to match the second order feature statistics with the target styles, which achieved real-time brush-size control in a purely feed-forward manner for style transfer.
Proceedings ArticleDOI
Wide-Slice Residual Networks for Food Recognition
TL;DR: In this paper, a slice convolution block is introduced to capture vertical food traits that are common to a large number of categories (i.e., 15% of the whole data in current datasets).
Journal ArticleDOI
Remote Sensing Scene Classification by Gated Bidirectional Network
TL;DR: A gated bidirectional network is proposed to integrate the hierarchical feature aggregation and the interference information elimination into an end-to-end network and can compete with the state-of-the-art methods on four RS scene classification data sets.
Journal ArticleDOI
Fusing Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks
TL;DR: This work proposes a multistream LSTM architecture with a new smoothed score fusion technique to learn classification from different geometric feature streams and observes that the geometric relational features based on distances between joints and selected lines outperform other features and achieve the state-of-the-art performance on four datasets.
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.