ImageNet: A large-scale hierarchical image database
Citations
23 citations
Cites background from "ImageNet: A large-scale hierarchica..."
...A notable insight of their work is the fact that convolutional networks based on optical flow features can be fine tuned from DCNs taught on RGB inputs, such as that used for image classification on the ImageNet dataset [11]....
[...]
23 citations
Cites methods from "ImageNet: A large-scale hierarchica..."
...Specifically, we adopt the weights of ResNeXt-101-FPN [27, 48] trained on ImageNet [7] to initialize the parameters of the backbone network, and train our framework on two GeForce GTX 1080 Ti GPUs (four images per GPU) for 40k training iterations....
[...]
23 citations
23 citations
23 citations
References
46,906 citations
"ImageNet: A large-scale hierarchica..." refers methods in this paper
...SIFT [15] descriptors are used in this experiment....
[...]
13,049 citations
"ImageNet: A large-scale hierarchica..." refers background or methods in this paper
...ImageNet uses the hierarchical structure of WordNet [9]....
[...]
...The main asset of WordNet [9] lies in its semantic structure, i....
[...]
5,742 citations
"ImageNet: A large-scale hierarchica..." refers methods in this paper
...Special purpose datasets, such as FERET faces [19], Labeled faces in the Wild [13] and the Mammal Benchmark by Fink and Ullman [11] are not included....
[...]
4,302 citations
"ImageNet: A large-scale hierarchica..." refers background in this paper
...Rosch and Lloyd [ 20 ] have demonstrated that humans tend to label visual objects at an easily accessible semantic level termed as “basic level” (e.g....
[...]
4,024 citations
Additional excerpts
...[16, 17, 28, 18])....
[...]