End-to-end scene text recognition
Citations
5,978 citations
Additional excerpts
...Furthermore we demonstrate that the CAM localization technique generalizes to other visual recognition tasks i.e., our technique produces generic localizable deep features that can aid other researchers in understanding the basis of discrimination used by CNNs for their tasks....
[...]
5,311 citations
Cites background from "End-to-end scene text recognition"
...Indeed, only recently have end-to-end systems become a target of focused research [6, 7]....
[...]
5,065 citations
2,184 citations
1,224 citations
Cites methods from "End-to-end scene text recognition"
...[19]) • Weakly Contextualised: a vocabulary of all words in the training/test set • Generic: a generic vocabulary of about 90K words derived from the dataset4 of Jaderberg et al....
[...]
References
31,952 citations
"End-to-end scene text recognition" refers methods in this paper
...We perform multi-scale character detection via sliding window classification; this approach has been extremely successful in face [19] and pedestrian [5] detection....
[...]
...We do this separately for each character using a simple greedy heuristic (similar to what is described in [9]): we iterate over all windows in the image in descending order of their score, and if the location has not yet been suppressed, we suppress all of its neighbors (i.e., windows that have an…...
[...]
22,840 citations
18,802 citations
"End-to-end scene text recognition" refers background in this paper
...A common simplification of this model is to assume that all features are conditionally independent (i.e., the Naive Bayes model [1]): p(x|c) = N∏ i=1 p(x[i]|c)....
[...]
18,620 citations
"End-to-end scene text recognition" refers methods in this paper
...We perform multi-scale character detection via sliding window classification; this approach has been extremely successful in face [19] and pedestrian [5] detection....
[...]
15,935 citations
"End-to-end scene text recognition" refers methods in this paper
...We follow the evaluation guidelines outlined in [13], which are essentially the same as the evaluation guidelines of other object recognition competitions, like PASCAL VOC [8]....
[...]