37 citations · 75 across the 12 of their papers we have counts for
14 papers · 1 filter
DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents
Fuxiao Liu, Hao Tan, Chris Tensmeyer
Vision-language pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-…
MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Zilong Wang, Jiuxiang Gu, Chris Tensmeyer +5
Document images are a ubiquitous source of data where the text is organized in a complex hierarchical structure ranging from fine granularity (e.g., words), medium granularity (e.g…
End-to-end Document Recognition and Understanding with Dessurt
Brian Davis, Bryan Morse, Bryan Price +3
We introduce Dessurt, a relatively simple document understanding transformer capable of being fine-tuned on a greater variety of document tasks than prior methods. It receives a do…
LAFITE: Towards Language-Free Training for Text-to-Image Generation
Yufan Zhou, Ruiyi Zhang, Changyou Chen +6
One of the major challenges in training text-to-image generation models is the need of a large number of high-quality image-text pairs. While image samples are often easily accessi…
Visual FUDGE: Form Understanding via Dynamic Graph Editing
Brian Davis, Bryan Morse, Brian Price +2
We address the problem of form understanding: finding text entities and the relationships/links between them in form images. The proposed FUDGE model formulates this problem on a g…
RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Kai Li, Curtis Wigington, Chris Tensmeyer +5
Cross-Domain Detection (XDD) aims to train an object detector using labeled image from a source domain but have good performance in the target domain with only unlabeled images. Ex…
Text and Style Conditioned GAN for Generation of Offline Handwriting Lines
Brian Davis, Chris Tensmeyer, Brian Price +3
This paper presents a GAN for generating images of handwritten lines conditioned on arbitrary text and latent style vectors. Unlike prior work, which produce stroke points or singl…
Cross-Domain Document Object Detection: Benchmark Suite and Method
Kai Li, Curtis Wigington, Chris Tensmeyer +6
Decomposing images of document pages into high-level semantic regions (e.g., figures, tables, paragraphs), document object detection (DOD) is fundamental for downstream tasks like…
Deep Visual Template-Free Form Parsing
Brian Davis, Bryan Morse, Scott Cohen +2
Automatic, template-free extraction of information from form images is challenging due to the variety of form layouts. This is even more challenging for historical forms due to noi…
Language Model Supervision for Handwriting Recognition Model Adaptation
Chris Tensmeyer, Curtis Wigington, Brian Davis +3
Training state-of-the-art offline handwriting recognition (HWR) models requires large labeled datasets, but unfortunately such datasets are not available in all languages and domai…
PageNet: Page Boundary Extraction in Historical Handwritten Documents
Chris Tensmeyer, Brian Davis, Curtis Wigington +2
When digitizing a document into an image, it is common to include a surrounding border region to visually indicate that the entire document is present in the image. However, this b…
Convolutional Neural Networks for Font Classification
Chris Tensmeyer, Daniel Saunders, Tony Martinez
Classifying pages or text lines into font categories aids transcription because single font Optical Character Recognition (OCR) is generally more accurate than omni-font OCR. We pr…
Document Image Binarization with Fully Convolutional Neural Networks
Chris Tensmeyer, Tony Martinez
Binarization of degraded historical manuscript images is an important pre-processing step for many document processing tasks. We formulate binarization as a pixel classification le…
Analysis of Convolutional Neural Networks for Document Image Classification
Chris Tensmeyer, Tony Martinez
Convolutional Neural Networks (CNNs) are state-of-the-art models for document image classification tasks. However, many of these approaches rely on parameters and architectures des…