Vlad Morariu

Senior Research Scientist

Maryland

Vlad Morariu is a researcher at Adobe Research. His research interests involve combining computer vision, natural language, machine learning, and artificial intelligence techniques to develop rich visual and linguistic models that enable intelligent reasoning about images, videos, and related linguistic descriptions.

He received his PhD from the University of Maryland in 2010, with Professor Larry S. Davis as his advisor. Prior to that, he received the MS and BS degrees from the Pennsylvania State University in 2005, with Professor Octavia I. Camps as his thesis advisor. After completing his doctoral studies, he continued as a postdoctoral researcher and then as a research scientist at the University of Maryland until 2018, when he joined Adobe Research.

Publications

DocEditAgent: Document Structure Editing Via Multimodal LLM Grounding

Suri, M., Mathur, P., Dernoncourt, F., Jain, R., Morariu, V., Sawhney, R., Nakov, P., Manocha, D. (Nov. 16, 2024)

EMNLP 2024

DocScript: New Task, Dataset, and Models for Document-level Script Event Prediction

Mathur, P., Morariu, V., Garimella, A., Dernoncourt, F., Gu, J., Sawhney, R., Nakov, P., Manocha, D., Jain, R. (May. 25, 2024)

LREC-COLING 2024

DocEdit: Language-guided Document Editing

Mathur, P., Jain, R., Gu, J., Dernoncourt, F., Manocha, D., Morariu, V. (Feb. 14, 2023)

AAAI 2023

LayerDoc: Layer-wise Extraction of Spatial Hierarchical Structure in Visually-Rich Documents

Mathur, P., Jain, R., Mehra, A., Gu, J., Dernoncourt, F., Natarajan, A., Tran, Q., Kaynig-Fittkau, V., Nenkova, A., Manocha, D., Morariu, V. (Jan. 6, 2023)

WACV 2023

End-to-end Document Recognition and Understanding with Dessurt

Davis, B., Morse, B., Tensmeyer, C., Price, B., Wigington, C., Morariu, V. (Oct. 23, 2022)

TiE: Text in Everything (ECCV 2022 Workshop)

DocLayoutTTS: Dataset and Baselines for Layout-informed Document-level Neural Speech Synthesis

Mathur, P., Dernoncourt, F., Tran, Q., Gu, J., Nenkova, A., Morariu, V., Jain, R., Manocha, D. (Sep. 22, 2022)

Interspeech 2022

DocTime: A Document-level Temporal Dependency Graph Parser

Mathur, P., Morariu, V., Kaynig-Fittkau, V., Gu, J., Dernoncourt, F., Tran, Q., Nenkova, A., Manocha, D., Jain, R. (Jul. 15, 2022)

NAACL 2022

IGA: An Intent-Guided Authoring Assistant

Sun, S., Zhao, W., Manjunatha, V., Jain, R., Morariu, V., Dernoncourt, F., Srinivasan, B., Iyyer, M. (Nov. 9, 2021)

EMNLP 2021

TIMERS: Document-level Temporal Relation Extraction

Mathur, P., Jain, R., Dernoncourt, F., Morariu, V., Tran, Q., Manocha, D. (Aug. 4, 2021)

ACL 2021

Syntopical Graphs for Computational Argumentation Tasks

Barrow, J., Jain, R., Lipka, N., Dernoncourt, F., Morariu, V., Manjunatha, V., Oard, D., Resnik, P., Wachsmuth, H. (Aug. 4, 2021)

ACL 2021

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)

Layout-induced Video Representation for Recognizing Agent-in-Place Actions

Yu, R., Wang, H., Li, A., Zheng, J., Morariu, V., Davis, L. (Oct. 29, 2019)

International Conference on Computer Vision (ICCV)

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)

C-WSL: Count-guided Weakly Supervised Localization

Gao, M., Li, A., Yu, R., Morariu, V., Davis, L. (Sep. 10, 2018)

European Conference on Computer Vision (ECCV)

NISP: Pruning Networks using Neuron Importance Score Propagation

Yu, R., Li, A., Chen, C., Lai, J., Morariu, V., Han, X., Gao, M., Lin, C., Davis, L. (Jun. 21, 2018)

Spotlight

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition

Wang, Y., Morariu, V., Davis, L. (Jun. 20, 2018)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Dynamic Zoom-in Network for Fast Object Detection in Large Images

Gao, M., Yu, R., Li, A., Morariu, V., Davis, L. (Jun. 20, 2018)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Learning Rich Features for Image Manipulation Detection

Zhou, P., Han, X., Morariu, V., Davis, L. (Jun. 19, 2018)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Automatic online tuning for fast Gaussian summation

Morariu, V., Srinivasan, B., Raykar, V., Duraiswami, R., Davis, L. (Dec. 8, 2008)

22nd Annual Conference on Neural Information Processing Systems (NIPS)

News