Chris Tensmeyer

Research Scientist

Maryland

Chris joined the Document Intelligence Lab at Adobe Research in 2018 as a Research Scientist after performing a Summer research internship. He graduated with a PhD in computer science from Brigham Young University and developed new deep learning models to solve document analysis problems as part of his dissertation.  His research interests span a variety of document intelligence topics, including layout analysis and generation, text recognition, chart data extraction, and semantic understanding of documents.  The big project occupying most of his time deals with table understanding.  Deep learning models are his favorite hammer when confronted with a new nail (problem), but if the nail turns out to be, e.g., a screw, he has other tools in his toolbox too.

Publications

Web Table Formatting Affects Readability on Mobile Devices

Tensmeyer, C., Bylinskii, Z., Cai, T., Miller, D., Nenkova, A., Niklaus, A., Wallace, S. (Apr. 30, 2023)

Proceedings of the ACM Web Conference 2023

ICPR 2020 – Competition on Harvesting Raw Tables from Infographics

Tensmeyer, C., Shekhar, S., Singh, H., Davila, K., Setlur, S., Govindaraju, V. (Feb. 21, 2021)

ICPR 2021

Text and Style Conditioned GAN for Generation of Offline Handwriting Lines

Davis, B., Tensmeyer, C., Price, B., Wigington, C., Morse, B., Jain, R. (Sep. 7, 2020)

British Machine Vision Conference (BMVC)

Cross-Domain Document Object Detection: Benchmark Suite and Method

Li, K., Wigington, C., Tensmeyer, C., Zhao, H., Barmpalios, N., Morariu, V., Manjunatha, V., Sun, T., Fu, Y. (Jun. 22, 2020)

Conference on Computer Vision and Pattern Recognition (CVPR)

Historical Document Image Binarization – A Review

Tensmeyer, C., Martinez, T. (May. 16, 2020)

Springer Nature Computer Science

Generating Realistic Binarization Data with Generative Adversarial Networks

Tensmeyer, C., Brodie, M., Saunders, D., Martinez, T. (Nov. 11, 2019)

International Conference on Document Analysis and Recognition (ICDAR)

Training Full-Page Handwritten Text Recognition Models without Annotated Line Breaks

Tensmeyer, C., Wigington, C. (Nov. 11, 2019)

Oral

International Conference on Document Analysis and Recognition (ICDAR)

Robust Keypoint Regression

Tensmeyer, C., Martinez, T. (Nov. 9, 2019)

Long Oral

Workshop on Machine Learning (WML) at International Conference on Document Analysis and Recognition (ICDAR)

Deep Splitting and Merging for Table Structure Decomposition

Tensmeyer, C., Morariu, V., Price, B., Cohen, S., Martinez, T. (Sep. 23, 2019)

Oral

International Conference on Document Analysis and Recognition (ICDAR)

Deep Visual Template-Free Form Parsing

Davis, B., Morse, B., Cohen, S., Price, B., Tensmeyer, C. (Sep. 20, 2019)

Oral

International Conference on Document Analysis and Recognition (ICDAR)

ICDAR 2019 Competition on Harvesting Raw Tables from Infographics (CHART-Infographics)

Davila, K., Kota, B., Setlur, S., Govindraju, V., Tensmeyer, C., Shekhar, S., Chaudhry, R. (Sep. 20, 2019)

2019 International Conference on Document Analysis and Recognition

Start, Follow, Read: End-to-End Full-Page Handwriting Recognition

Wigington, C., Tensmeyer, C., Davis, B., Barrett, B., Price, B., Cohen, S. (Sep. 8, 2018)

European Conference on Computer Vision 2018

Language Model Supervision for Handwriting Recognition Model Adaptation

Tensmeyer, C., Wigington, C., Davis, B., Stewart, S., Martinez, T., Barrett, W. (Aug. 1, 2018)

International Conference on Frontiers in Handwriting Recognition

PageNet: Page Boundary Extraction in Historical Handwritten Documents

Tensmeyer, C., Davis, B., Wigington, C., Lee, I., Barrett, W. (Sep. 10, 2017)

International Workshop on Historical Document Imaging and Processing