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
Alleviating Over-segmentation Errors by Detecting Action Boundaries
TL;DR: A framework for temporal action segmentation, the ASRF, which divides temporal action segmentsation into frame-wise action classification and action boundary regression, and refines frame-level hypotheses of action classes using predicted action boundaries is proposed.
Journal ArticleDOI
STA-CNN: Convolutional Spatial-Temporal Attention Learning for Action Recognition
TL;DR: A Spatial-Temporal Attentive Convolutional Neural Network (STA-CNN) which selects the discriminative temporal segments and focuses on the informative spatial regions automatically and achieves the state-of-the-art performance on two of the most challenging datasets, UCF-101 and HMDB-51.
Posted Content
Deep Heterogeneous Feature Fusion for Template-Based Face Recognition
TL;DR: A deep heterogeneous feature fusion network to exploit the complementary information present in features generated by different deep convolutional neural networks for template-based face recognition, where a template refers to a set of still face images or video frames from different sources which introduces more blur, pose, illumination and other variations than traditional face datasets.
Journal ArticleDOI
Convolutional Invasion and Expansion Networks for Tumor Growth Prediction
TL;DR: Wang et al. as mentioned in this paper used deep convolutional neural networks (ConvNets) to directly represent and learn the cell invasion and mass-effect, and to predict the subsequent involvement regions of a tumor.
Journal ArticleDOI
Sensor-Based Human Activity Recognition with Spatio-Temporal Deep Learning.
TL;DR: In this article, a new methodology using convolution neural networks (CNN) with varying kernel dimensions along with bi-directional long short-term memory (BiLSTM) was introduced to capture features at various resolutions.
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.