Related papers: InkFM: A Foundational Model for Full-Page Online H…
Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of the entire page, or even multiple pages. Accordingly, this…
We present a new handwritten text segmentation method by training a convolutional neural network (CNN) in an end-to-end manner. Many conventional methods addressed this problem by extracting connected components and then classifying them.…
Online, real-time, and fine-grained 3D segmentation constitutes a fundamental capability for embodied intelligent agents to perceive and comprehend their operational environments. Recent advancements employ predefined object queries to…
Cardiac magnetic resonance imaging (CMR), considered the gold standard for noninvasive cardiac assessment, is a diverse and complex modality requiring a wide variety of image processing tasks for comprehensive assessment of cardiac…
Artificial intelligence (AI)-driven electronic design automation (EDA) techniques have been extensively explored for VLSI circuit design applications. Most recently, foundation AI models for circuits have emerged as a new technology trend.…
In a multilingual country like India where 12 different official scripts are in use, automatic identification of handwritten script facilitates many important applications such as automatic transcription of multilingual documents, searching…
Software developers maintain extensive mental models of code they produce and its context, often relying on memory to retrieve or reconstruct design decisions, edge cases, and debugging experiences. These missing links and data obstruct…
Humans can learn to solve new tasks by inducing high-level strategies from example solutions to similar problems and then adapting these strategies to solve unseen problems. Can we use large language models to induce such high-level…
Handwritten text recognition is an open problem of great interest in the area of automatic document image analysis. The transcription of handwritten content present in digitized documents is significant in analyzing historical archives or…
Doctors typically write in incomprehensible handwriting, making it difficult for both the general public and some pharmacists to understand the medications they have prescribed. It is not ideal for them to write the prescription quietly and…
Handwritten digit recognition is one of the extensively studied area in machine learning. Apart from the wider research on handwritten digit recognition on MNIST dataset, there are many other research works on various script recognition.…
Automatically recognizing the layout of handwritten documents is an important step towards useful extraction of information from those documents. The most common application is to feed downstream applications such as automatic text…
High-quality labeled data is essential for training accurate document conversion models, particularly in domains with complex formats such as tables, formulas, and multi-column text. However, manual annotation is both costly and…
Foundation models, such as Large Language Models (LLMs) or Large Vision Models (LVMs), have emerged as one of the most powerful tools in the respective fields. However, unlike text and image data, graph data do not have a definitive…
In this paper, we demonstrate how a generative model can be used to build a better recognizer through the control of content and style. We are building an online handwriting recognizer from a modest amount of training samples. By training…
Handwriting recognition is one of the desirable attributes of document comprehension and analysis. It is concerned with the documents writing style and characteristics that distinguish the authors. The diversity of text images, notably in…
Handwritten Chinese text recognition (HCTR) has been an active research topic for decades. However, most previous studies solely focus on the recognition of cropped text line images, ignoring the error caused by text line detection in…
Multimodal Large Language Models (MLLMs) have shown impressive results on various multimodal tasks. However, most existing MLLMs are not well suited for document-oriented tasks, which require fine-grained image perception and information…
We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms. The dataset comprises 199 real, fully annotated, scanned forms. The documents are noisy…
Offline Handwritten Text Recognition (HTR) systems play a crucial role in applications such as historical document digitization, automatic form processing, and biometric authentication. However, their performance is often hindered by the…