Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
1,203 citations
1,203 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...Our method with VggNet image representation (Simonyan & Zisserman (2014)) outperforms the state-of-the-art methods, including the very recently released methods, in almost all the evaluation metrics....
[...]
...Recently, Simonyan & Zisserman (2014) propose a CNN with over 16 layers (denoted as VggNet) and performs substantially better than the AlexNet....
[...]
...The mRNN model with VggNet performs better than that with AlexNet, which indicates the importance 6We only select the word with maximum probability each time in the sentence generation process while many comparing methods (e.g. DMSM, NIC, LRCN) uses a beam search scheme that keeps the best K candidates....
[...]
...For the vision part, we use the pre-trained AlexNet (Krizhevsky et al. (2012)) or the VggNet (Simonyan & Zisserman (2014)) on ImageNet dataset (Russakovsky et al. (2014))....
[...]
...For the image representation, here we use the activation of the 7th layer of AlexNet (Krizhevsky et al. (2012)) or 15th layer of VggNet (Simonyan & Zisserman (2014)), though our framework can use any image features....
[...]
1,203 citations
1,201 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...Using VGG16 [18] as a motivating example: VGG16 contains 16 layers....
[...]
1,175 citations
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations