Search Results for author:
Found 20 papers, 7 papers with code
Good News, Everyone! Context driven entity-aware captioning for news images
We propose a novel captioning method that is able to leverage contextual information provided by the text of news articles associated with an image.
TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces
We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration.
Single Shot Scene Text Retrieval
In this way, the text based image retrieval task can be casted as a simple nearest neighbor search of the query text representation over the outputs of the CNN over the entire image database.
GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images
We propose a novel method that is able to produce credible handwritten word images by conditioning the generative process with both calligraphic style features and textual content.
Scene Text Visual Question Answering
Current visual question answering datasets do not consider the rich semantic information conveyed by text within an image.
Selective Style Transfer for Text
This paper explores the possibilities of image style transfer applied to text maintaining the original transcriptions.
STEP -- Towards Structured Scene-Text Spotting
We introduce the structured scene-text spotting task, which requires a scene-text OCR system to spot text in the wild according to a query regular expression.
The Robust Reading Competition Annotation and Evaluation Platform
The ICDAR Robust Reading Competition (RRC), initiated in 2003 and re-established in 2011, has become a de-facto evaluation standard for robust reading systems and algorithms.
Self-supervised learning of visual features through embedding images into text topic spaces
End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible.
Self-Supervised Visual Representations for Cross-Modal Retrieval
Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places.
ICDAR 2019 Competition on Scene Text Visual Question Answering
ST-VQA introduces an important aspect that is not addressed by any Visual Question Answering system up to date, namely the incorporation of scene text to answer questions asked about an image.
Unsupervised Adaptation for Synthetic-to-Real Handwritten Word Recognition
Handwritten Text Recognition (HTR) is still a challenging problem because it must deal with two important difficulties: the variability among writing styles, and the scarcity of labelled data.
Candidate Fusion: Integrating Language Modelling into a Sequence-to-Sequence Handwritten Word Recognition Architecture
The main challenge faced when training a language model is to deal with the language model corpus which is usually different to the one used for training the handwritten word recognition system.
Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition
Sequential architectures are a perfect fit to model text lines, not only because of the inherent temporal aspect of text, but also to learn probability distributions over sequences of characters and words.
Ranked #8 on
Handwritten Text Recognition
on IAM
Multimodal grid features and cell pointers for Scene Text Visual Question Answering
This paper presents a new model for the task of scene text visual question answering, in which questions about a given image can only be answered by reading and understanding scene text that is present in it.
Content and Style Aware Generation of Text-line Images for Handwriting Recognition
Once properly trained, our method can also be adapted to new target data by only accessing unlabeled text-line images to mimic handwritten styles and produce images with any textual content.
VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification
Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task.
Ranked #18 on
Document Image Classification
on RVL-CDIP
EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification
To the best of our knowledge, this is the first time to leverage a mutual learning approach along with a self-attention-based fusion module to perform document image classification.
Ranked #1 on
Document Image Classification
on RVL-CDIP
TransferDoc: A Self-Supervised Transferable Document Representation Learning Model Unifying Vision and Language
The field of visual document understanding has witnessed a rapid growth in emerging challenges and powerful multi-modal strategies.
Ranked #19 on
Document Image Classification
on RVL-CDIP
Visual and Textual Deep Feature Fusion for Document Image Classification
Moreover, a joint feature learning approach that combines image features and text embeddings is introduced as a late fusion methodology.
Ranked #2 on
Document Image Classification
on RVL-CDIP
