English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large models have recently played a dominant role in natural languageprocessing and multimodal vision-language learning. However, theireffectiveness in text-related visual tasks remains relatively unexplored. Inthis paper, we conducted a comprehensive evaluation of Large Multimodal Models,such as GPT4V and Gemini, in various text-related visual tasks including TextRecognition, Scene Text-Centric Visual Question Answering (VQA),Document-Oriented VQA, Key Information Extraction (KIE), and HandwrittenMathematical Expression Recognition (HMER). To facilitate the assessment ofOptical Character Recognition (OCR) capabilities in Large Multimodal Models, wepropose OCRBench, a comprehensive evaluation benchmark.Our study encompasses 29datasets, making it the most comprehensive OCR evaluation benchmark available.Furthermore, our study reveals both the strengths and weaknesses of thesemodels, particularly in handling multilingual text, handwritten text,non-semantic text, and mathematical expression recognition. Most importantly,the baseline results showcased in this study could provide a foundationalframework for the conception and assessment of innovative strategies targetedat enhancing zero-shot multimodal techniques. The evaluation pipeline andbenchmark are available at https://github.com/Yuliang-Liu/MultimodalOCR.

On the Hidden Mystery of OCR in Large Multimodal Models