Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
477 citations
476 citations
476 citations
Cites background from "Very Deep Convolutional Networks fo..."
...Convolutional neural networks (CNN) have been successfully applied to several diverse classification problems including speech and image recognition [1][2][3]....
[...]
...In the literature large sized deep networks [1][2][3] have achieved state-of-the-art performance on various challenging tasks....
[...]
...Large, deep Convolutional Neural Networks (CNN) have been successfully applied to diverse classification problems including speech and image recognition [Simonyan and Zisserman 2014; Krizhevsky et al. 2012; Hinton et al. 2012]....
[...]
474 citations
474 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...Deep learning approaches have recently been used to learn video representations and have produced state-of-art results (Karpathy et al., 2014; Simonyan & Zisserman, 2014a; Wang et al., 2015b; Tran et al., 2014)....
[...]
...We follow the training procedure introduced by the two-stream framework Simonyan & Zisserman (2014a)....
[...]
...VGG-16 CNNs are pretrained on ImageNet (Simonyan & Zisserman, 2014b) and fine-tuned on the UCF-101 dataset, following the protocol in Wang et al. (2015b)....
[...]
...As it has been shown that characterizing entities in addition of action is important for the caption-generation task Yao et al. (2015a), we also use as encoder a CNN Szegedy et al. (2014), pretrained on ImageNet, that focuses on detecting static visual object categories....
[...]
...Simonyan & Zisserman (2014a) introduced a two-stream framework where they train CNNs independently on RGB and optical flow inputs....
[...]
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations