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
Journal ArticleDOI
Automatic Construction of Chinese Herbal Prescriptions From Tongue Images Using CNNs and Auxiliary Latent Therapy Topics
TL;DR: Wang et al. as mentioned in this paper proposed a neural network framework for automatic construction of herbal prescriptions from tongue images, which includes single/double convolution channels and fully connected layers to model the therapy of Chinese doctors and alleviate the interference of sparse output labels on the diversity of results.
Journal ArticleDOI
Deep3DSaliency: Deep Stereoscopic Video Saliency Detection Model by 3D Convolutional Networks
TL;DR: A novel stereoscopic saliency detection method based on 3D convolutional neural networks, namely, deep 3D video saliency (Deep3DSaliency) is proposed, which shows the superior performance of the proposed model over other existing ones in saliency estimation for3D video sequences.
Posted ContentDOI
RGB-D Data-based Action Recognition: A Review
TL;DR: This review is aimed to scope current literature on data-fusion and action-recognition techniques and to identify gaps and future research direction, as well as discussing research challenges, emerging trends, and possible future research directions.
Journal ArticleDOI
Few-shot activity recognition with cross-modal memory network
Lingling Zhang,Lingling Zhang,Xiaojun Chang,Jun Liu,Minnan Luo,Mahesh Prakash,Alexander G. Hauptmann +6 more
TL;DR: This paper proposes a novel end-to-end cross-modal memory network for few-shot activity recognition that stores the dynamic visual and textual semantics for some high-level attributes related to human activities and could achieve significant improvements over other previous methods.
Journal ArticleDOI
Discriminative Part Selection for Human Action Recognition
TL;DR: Improved performance is achieved by more elegantly addressing the correlation among parts and refinement of the candidate space by applying a maximum margin model, which can alleviate overfitting while simultaneously improving generalizability and correlation extraction.
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.