Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
449 citations
448 citations
Additional excerpts
...The proposed network is built upon the HED [42] architecture and choses VGG16 [36] as backbone....
[...]
...The proposed network is built upon the HED [5] architecture and choses VGG16 [34] as backbone....
[...]
448 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...For pedestrian detection, we use the pretrained VGG-16 model [35] as adopted in [41]....
[...]
448 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...After the classification was computed, slow cells were associated using only motion features, since they were almost still, while fast cells were associated using both motion features and visual features extracted by a Fast R-CNN based on VGG-16 [1], specifically fine-tuned for the cell classification task....
[...]
...Convolutional neural networks (CNN) currently constitute the state-of-the-art in spatial pattern extraction, and are employed in tasks such as image classification [1, 2, 3] or object detection [4, 5, 6], while recurrent neural networks (RNN) like the Long Short-Term Memory (LSTM) are used to process sequential data, like audio signals, temporal series and text [7, 8, 9, 10]....
[...]
...After this step, an actual association step was performed by using VGG-16 features given as input to a Siamese LSTM, that predicted an affinity score between the tracklet and the detections....
[...]
...The input of this RNN was a visual features vector extracted by a VGG CNN [1], pretrained specifically for person re-identification....
[...]
447 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...We use the pre-trained 19-layer VGG-Network from [24]....
[...]
...inatively trained deep convolutional neural networks have recently made dramatic impact [13, 24]....
[...]
...[7, 8] have recently demonstrated remarkable results for transferring styles to guiding “content” images: Their method uses the filter pyramid of the VGG network [24] as a higher-level representation of images, benefitting from the vast knowledge acquired through training the dCNN on millions of photographs....
[...]
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations