Curtis Wigington
Research Subjects
Curtis Wigington has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Chris Tensmeyer
Adobe Research
5 shared publications - Brian Price
Adobe Research
3 shared publications - Bryan Morse
Brigham Young University
3 shared publications - Vlad I. Morariu
Adobe Research
3 shared publications - Brian Davis
Brigham Young University Provo UT USA
2 shared publications - Tong Sun
Adobe Research
2 shared publications
Latest Publications
- Open Access
Handheld Video Document Scanning: A Robust On-Device Model for Multi-Page Document Scanning
Document capture applications on smartphones have emerged as popular tools for digitizing documents. For many individuals, capturing documents with their smartphones is more convenient than using dedicated photocopiers or scanners, even if the quality of digitization is lower. However, using a smartphone for digitization can become excessively time-consuming and tedious when a user needs to digitize a document with multiple pages. In this work, we propose a novel approach to automatically scan multi-page documents from a video stream as the user turns through the pages of the document. Unlike previous methods that required constrained settings such as mounting the phone on a tripod, our technique is designed to allow the user to hold the phone in their hand. Our technique is trained to be robust to the motion and instability inherent in handheld scanning. Our primary contributions in this work include: (1) an efficient, on-device deep learning model that is accurate and robust for handheld scanning, (2) a novel data collection and annotation technique for video document scanning, and (3) state-of-the-art results on the PUCIT page turn dataset.
Open AccessHandheld Video Document Scanning: A Robust On-Device Model for Multi-Page Document Scanning
Document capture applications on smartphones have emerged as popular tools for digitizing documents. For many individuals, capturing documents with their smartphones is more convenient than using dedicated photocopiers or scanners, even if the quality of digitization is lower. However, using a smartphone for digitization can become excessively time-consuming and tedious when a user needs to digitize a document with multiple pages. In this work, we propose a novel approach to automatically scan multi-page documents from a video stream as the user turns through the pages of the document. Unlike previous methods that required constrained settings such as mounting the phone on a tripod, our technique is designed to allow the user to hold the phone in their hand. Our technique is trained to be robust to the motion and instability inherent in handheld scanning. Our primary contributions in this work include: (1) an efficient, on-device deep learning model that is accurate and robust for handheld scanning, (2) a novel data collection and annotation technique for video document scanning, and (3) state-of-the-art results on the PUCIT page turn dataset.
- 14 February 2023
- Published by Springer Nature
- p. 280-296
End-to-End Document Recognition and Understanding with Dessurt
- 14 February 2023
- Published by Springer Nature
- p. 280-296
End-to-End Document Recognition and Understanding with Dessurt
- 10 December 2022
- Published by Springer Nature
- p. 3-17
Secure and Efficient Agreement Signing Atop Blockchain and Decentralized Identity
- 10 December 2022
- Published by Springer Nature
- p. 3-17
Secure and Efficient Agreement Signing Atop Blockchain and Decentralized Identity
- Open Access
End-to-end Document Recognition and Understanding with Dessurt
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 document image and task string as input and generates arbitrary text autoregressively as output. Because Dessurt is an end-to-end architecture that performs text recognition in addition to the document understanding, it does not require an external recognition model as prior methods do. Dessurt is a more flexible model than prior methods and is able to handle a variety of document domains and tasks. We show that this model is effective at 9 different dataset-task combinations.
Open AccessEnd-to-end Document Recognition and Understanding with Dessurt
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 document image and task string as input and generates arbitrary text autoregressively as output. Because Dessurt is an end-to-end architecture that performs text recognition in addition to the document understanding, it does not require an external recognition model as prior methods do. Dessurt is a more flexible model than prior methods and is able to handle a variety of document domains and tasks. We show that this model is effective at 9 different dataset-task combinations.
- Open Access
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 20-25
TELIN: Table Entity LINker for Extracting Leaderboards from Machine Learning Publications
Sean Yang, Chris Tensmeyer, Curtis Wigington. Proceedings of the first Workshop on Information Extraction from Scientific Publications. 2022.
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 20-25
Open AccessTELIN: Table Entity LINker for Extracting Leaderboards from Machine Learning Publications
Sean Yang, Chris Tensmeyer, Curtis Wigington. Proceedings of the first Workshop on Information Extraction from Scientific Publications. 2022.
- Open Access
Visual FUDGE: Form Understanding via Dynamic Graph Editing
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 graph of text elements (the vertices) and uses a Graph Convolutional Network to predict changes to the graph. The initial vertices are detected text lines and do not necessarily correspond to the final text entities, which can span multiple lines. Also, initial edges contain many false-positive relationships. FUDGE edits the graph structure by combining text segments (graph vertices) and pruning edges in an iterative fashion to obtain the final text entities and relationships. While recent work in this area has focused on leveraging large-scale pre-trained Language Models (LM), FUDGE achieves almost the same level of entity linking performance on the FUNSD dataset by learning only visual features from the (small) provided training set. FUDGE can be applied on forms where text recognition is difficult (e.g. degraded or historical forms) and on forms in resource-poor languages where pre-training such LMs is challenging. FUDGE is state-of-the-art on the historical NAF dataset.
Open AccessVisual FUDGE: Form Understanding via Dynamic Graph Editing
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 graph of text elements (the vertices) and uses a Graph Convolutional Network to predict changes to the graph. The initial vertices are detected text lines and do not necessarily correspond to the final text entities, which can span multiple lines. Also, initial edges contain many false-positive relationships. FUDGE edits the graph structure by combining text segments (graph vertices) and pruning edges in an iterative fashion to obtain the final text entities and relationships. While recent work in this area has focused on leveraging large-scale pre-trained Language Models (LM), FUDGE achieves almost the same level of entity linking performance on the FUNSD dataset by learning only visual features from the (small) provided training set. FUDGE can be applied on forms where text recognition is difficult (e.g. degraded or historical forms) and on forms in resource-poor languages where pre-training such LMs is challenging. FUDGE is state-of-the-art on the historical NAF dataset.
- Open Access
Cross-Domain Document Object Detection: Benchmark Suite and Method
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 intelligent document editing and understanding. DOD remains a challenging problem as document objects vary significantly in layout, size, aspect ratio, texture, etc. An additional challenge arises in practice because large labeled training datasets are only available for domains that differ from the target domain. We investigate cross-domain DOD, where the goal is to learn a detector for the target domain using labeled data from the source domain and only unlabeled data from the target domain. Documents from the two domains may vary significantly in layout, language, and genre. We establish a benchmark suite consisting of different types of PDF document datasets that can be utilized for cross-domain DOD model training and evaluation. For each dataset, we provide the page images, bounding box annotations, PDF files, and the rendering layers extracted from the PDF files. Moreover, we propose a novel cross-domain DOD model which builds upon the standard detection model and addresses domain shifts by incorporating three novel alignment modules: Feature Pyramid Alignment (FPA) module, Region Alignment (RA) module and Rendering Layer alignment (RLA) module. Extensive experiments on the benchmark suite substantiate the efficacy of the three proposed modules and the proposed method significantly outperforms the baseline methods. The project page is at \url{https://github.com/kailigo/cddod}.
Open AccessCross-Domain Document Object Detection: Benchmark Suite and Method
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 intelligent document editing and understanding. DOD remains a challenging problem as document objects vary significantly in layout, size, aspect ratio, texture, etc. An additional challenge arises in practice because large labeled training datasets are only available for domains that differ from the target domain. We investigate cross-domain DOD, where the goal is to learn a detector for the target domain using labeled data from the source domain and only unlabeled data from the target domain. Documents from the two domains may vary significantly in layout, language, and genre. We establish a benchmark suite consisting of different types of PDF document datasets that can be utilized for cross-domain DOD model training and evaluation. For each dataset, we provide the page images, bounding box annotations, PDF files, and the rendering layers extracted from the PDF files. Moreover, we propose a novel cross-domain DOD model which builds upon the standard detection model and addresses domain shifts by incorporating three novel alignment modules: Feature Pyramid Alignment (FPA) module, Region Alignment (RA) module and Rendering Layer alignment (RLA) module. Extensive experiments on the benchmark suite substantiate the efficacy of the three proposed modules and the proposed method significantly outperforms the baseline methods. The project page is at \url{https://github.com/kailigo/cddod}.
- 6 October 2018
- Published by Springer Nature
- p. 372-388
Start, Follow, Read: End-to-End Full-Page Handwriting Recognition
- 6 October 2018
- Published by Springer Nature
- p. 372-388
Start, Follow, Read: End-to-End Full-Page Handwriting Recognition