The field of visual document understanding has witnessed a rapid growth ...
We introduce the structured scene-text spotting task, which requires a
s...
In the recent past, complex deep neural networks have received huge inte...
Multimodal learning from document data has achieved great success lately...
Handwritten Text Recognition has achieved an impressive performance in p...
The advent of recurrent neural networks for handwriting recognition mark...
Perceiving text is crucial to understand semantics of outdoor scenes and...
Although current image generation methods have reached impressive qualit...
Sequence-to-sequence models have recently become very popular for tackli...
Handwritten Text Recognition (HTR) is still a challenging problem becaus...
This paper presents final results of ICDAR 2019 Scene Text Visual Questi...
This paper explores the possibilities of image style transfer applied to...
Current visual question answering datasets do not consider the rich sema...
Current image captioning systems perform at a merely descriptive level,
...
Cross-modal retrieval methods have been significantly improved in last y...
Textual information found in scene images provides high level semantic
i...
The immense success of deep learning based methods in computer vision he...
The ICDAR Robust Reading Competition (RRC), initiated in 2003 and
re-est...
End-to-end training from scratch of current deep architectures for new
c...