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
Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
TL;DR: STFT blocks based 3D CNNs achieve on par or even better performance compared to the state-of-the-art methods, and their feature learning capabilities are significantly better than the conventional 3D convolutional layer and its variants.
Journal ArticleDOI
Memory-Augmented Temporal Dynamic Learning for Action Recognition
Yuan Yuan,Dong Wang,Qi Wang +2 more
TL;DR: In this paper, a memory-augmented temporal dynamic learning network is proposed, which learns to write the most evident information into an external memory module and ignore irrelevant ones by using a differential memory controller to make a discrete decision on whether the external memory should be updated with current feature.
Journal ArticleDOI
Iterative weak/self-supervised classification framework for abnormal events detection
Bruno Degardin,Hugo Proença +1 more
TL;DR: In this article, the authors proposed an iterative learning framework composed of two experts working in the weak and self-supervised paradigms and providing additional amounts of learning data to each other, where the novel instances at each iteration are filtered by a Bayesian framework that supports the iterative data augmentation task.
Journal ArticleDOI
Spatiotemporal Relation Networks for Video Action Recognition
Zheng Liu,Haifeng Hu +1 more
TL;DR: A new end-to-end architecture called SpatioTemporal Relation Networks (STRN) to extract spatial information and temporal information simultaneously from the video with the only RGB input, which avoids the calculation of optical flow.
Proceedings ArticleDOI
Recurrent Assistance: Cross-Dataset Training of LSTMs on Kitchen Tasks
Toby Perrett,Dima Damen +1 more
TL;DR: It is shown that transferring, by pre-training on similar datasets using label concatenation, delivers improved frame-based classification accuracy and faster training convergence than random initialisation.
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.