Related papers: TextOCR: Towards large-scale end-to-end reasoning …

Visual Place Recognition (VPR) in long-term deployment requires reasoning beyond pixel similarity: systems must make transparent, interpretable decisions that remain robust under lighting, weather and seasonal change. We present Text2Graph…

The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. While page-level chunking and retrieval is a natural starting…

Text in curve orientation, despite being one of the common text orientations in real world environment, has close to zero existence in well received scene text datasets such as ICDAR2013 and MSRA-TD500. The main motivation of Total-Text is…

Diffusion-based scene text synthesis has progressed rapidly, yet existing methods commonly rely on additional visual conditioning modules and require large-scale annotated data to support multilingual generation. In this work, we revisit…

This paper discusses the challenges of optical character recognition (OCR) on natural scenes, which is harder than OCR on documents due to the wild content and various image backgrounds. We propose to uniformly use word error rates (WER) as…

Typical text recognition methods rely on an encoder-decoder structure, in which the encoder extracts features from an image, and the decoder produces recognized text from these features. In this study, we propose a simpler and more…

Numerous scene text detection methods have been proposed in recent years. Most of them declare they have achieved state-of-the-art performances. However, the performance comparison is unfair, due to lots of inconsistent settings (e.g.,…

In this paper, we propose a pixel-wise method named TextCohesion for scene text detection, which splits a text instance into five key components: a Text Skeleton and four Directional Pixel Regions. These components are easier to handle than…

Scene text recognition with arbitrary shape is very challenging due to large variations in text shapes, fonts, colors, backgrounds, etc. Most state-of-the-art algorithms rectify the input image into the normalized image, then treat the…

The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability in their training…

Document comparison typically relies on optical character recognition (OCR) as its core technology. However, OCR requires the selection of appropriate language models for each document and the performance of multilingual or hybrid models…

In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above. SMA first uses a structural graph representation to encode the object-object, object-text and text-text…

Event stream based scene text recognition is a newly arising research topic in recent years which performs better than the widely used RGB cameras in extremely challenging scenarios, especially the low illumination, fast motion. Existing…

We present Multimodal OCR (MOCR), a document parsing paradigm that jointly parses text and graphics into unified textual representations. Unlike conventional OCR systems that focus on text recognition and leave graphical regions as cropped…

Image-text matching has been a hot research topic bridging the vision and language areas. It remains challenging because the current representation of image usually lacks global semantic concepts as in its corresponding text caption. To…

Previous deep learning based state-of-the-art scene text detection methods can be roughly classified into two categories. The first category treats scene text as a type of general objects and follows general object detection paradigm to…

Diacritic characters can be considered as a unique set of characters providing us with adequate and significant clue in identifying a given language with considerably high accuracy. Diacritics, though associated with phonetics often serve…

Optical character recognition (OCR) has advanced rapidly with the rise of vision-language models, yet evaluation has remained concentrated on a small cluster of high- and mid-resource scripts. We introduce GlotOCR Bench, a comprehensive…

Synthetic image generation has recently experienced significant improvements in domains such as natural image or art generation. However, the problem of figure and diagram generation remains unexplored. A challenging aspect of generating…

Printed text recognition is an important problem for industrial OCR systems. Printed text is constructed in a standard procedural fashion in most settings. We develop a mathematical model for this process that can be applied to the backward…