Automatic Image Annotation using Deep Learning Representations
Citations
428 citations
377 citations
260 citations
152 citations
149 citations
Cites background from "Automatic Image Annotation using De..."
...In general, CNNs and deeplearning currently form one of the fastest growing areas of computer science, and have been widely applied to various tasks such as image labeling [86], style-transfer [87] and even playing games against professional human players [88]....
[...]
References
73,978 citations
55,235 citations
"Automatic Image Annotation using De..." refers methods in this paper
...Here CNN features are extracted for images using a pretrained VGG-16 [26] network, and the word embedding vector for a tag is extracted using a pre-trained Skip-gram architecture (Word2Vec) [19]; both these networks are publicly available....
[...]
...Features extracted from Caffe-Net provided by Caffe [7] (similar to AlexNet [9]) did not work as well as VGG-16, hence we used VGG-16 features for all our experiments....
[...]
...Here CNN features are extracted for images using a pre-trained VGG-16 [14] network, and the word embedding vector for a tag is extracted using a pre-trained skip-gram architecture (word2vec of [11]); both these networks are publicly available....
[...]
...Inspired by the success of deep CNN architectures [16, 26, 6] on the large scale image classification task [25] we intend to make use of this powerful architecture to solve the task of automatic image annotation....
[...]
...We explored both VGG-16 and VGG-19 layered architecture features....
[...]
49,914 citations
20,077 citations
13,081 citations
"Automatic Image Annotation using De..." refers methods in this paper
...CNN features are shown to be successful for most of the vision tasks producing significantly improved results on the most challenging datasets like PASCAL VOC and ILSVRC2013 [6, 24]....
[...]
...Inspired by the success of deep CNN architectures [16, 26, 6] on the large scale image classification task [25] we intend to make use of this powerful architecture to solve the task of automatic image annotation....
[...]