# WordVIS: A Color Worth A Thousand Words

arXiv: https://arxiv.org/abs/2412.10155 · HTML: https://mlsanity.com/paper/2412.10155/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Builds on (most cited first, 6 of 6)

- [Chargrid: Towards Understanding 2D Documents](https://mlsanity.com/paper/1809.08799/) (2018)
- [PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks](https://mlsanity.com/paper/2004.07464/) (2020)
- [BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding](https://mlsanity.com/paper/1909.04948/) (2019)
- [ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents](https://mlsanity.com/paper/2105.11672/) (2021)
- [Multimodal deep networks for text and image-based document classification](https://mlsanity.com/paper/1907.06370/) (2019)
- [Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification](https://mlsanity.com/paper/1704.03557/) (2017)

## Abstract (arXiv)

Document classification is considered a critical element in automated document processing systems. In recent years multi-modal approaches have become increasingly popular for document classification. Despite their improvements, these approaches are underutilized in the industry due to their requirement for a tremendous volume of training data and extensive computational power. In this paper, we attempt to address these issues by embedding textual features directly into the visual space, allowing lightweight image-based classifiers to achieve state-of-the-art results using small-scale datasets in document classification. To evaluate the efficacy of the visual features generated from our approach on limited data, we tested on the standard dataset Tobacco-3482. Our experiments show a tremendous improvement in image-based classifiers, achieving an improvement of 4.64% using ResNet50 with no document pre-training. It also sets a new record for the best accuracy of the Tobacco-3482 dataset with a score of 91.14% using the image-based DocXClassifier with no document pre-training. The simplicity of the approach, its resource requirements, and subsequent results provide a good prospect for its use in industrial use cases.