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
Learning Spatiotemporal Features for Infrared Action Recognition with 3D Convolutional Neural Networks
TL;DR: Li et al. as discussed by the authors proposed a two-stream 3D convolutional neural network architecture by introducing the discriminative code layer and the corresponding discrimINative code loss function. And the proposed network processes IR images and the IR-based optical flow field sequences.
Journal ArticleDOI
Temporal and Fine-Grained Pedestrian Action Recognition on Driving Recorder Database
TL;DR: The paper thoroughly evaluated several types of configurations to explore an effective approach in fine-grained pedestrian action recognition without a large-scale database and found out how to learn an effective recognition model with only a small-scaledatabase.
Journal ArticleDOI
Pose-based deep gait recognition
Anna Sokolova,Anton Konushin +1 more
TL;DR: In this article, a pose-based convolutional neural network model was proposed for gait recognition, which considers the motion of points in the areas around human joints to extract motion information.
Proceedings ArticleDOI
Video Multitask Transformer Network
TL;DR: The Multitask Transformer Network, a repurposed model of the Transformer for video, modified the concept of query which was specialized only for action recognition on the trimmed video to fit the untrimmed video and utilized the class conversion matrix (CCM) to share the information of different tasks.
Journal ArticleDOI
Dense Dilated Network for Video Action Recognition
TL;DR: A dense dilated network to collect action information from snippet-level to global-level by fusing outputs from each layer to learn high-level representations, and these representations are robust even with only a few training snippets.
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.