Margrit Betke's Homepage at Boston University

PhD applicants: No new students

AI & Emerging Media

BU AIR @ HIC

OLD Camera Mouse Website

Women in CS

Margrit Betke, Professor, Department of Computer Science

Short Bio and Funding,

Long CV

Education:	Ph.D. in Computer Science and Electrical Engineering, Massachusetts Institute of Technology
Research:	Computer vision, human-computer interfaces, medical image analysis, and machine learning. Sample projects: Exciting news: We have a new Camera Mouse!!! You can try it out by downloading the Windows executable of the Boston University Camera Mouse. More info at our GitHub page of the BU Camera Mouse, Video-based interfaces for people with disabilities, spring 2024, Fri 1-2 pm. Zoom. AI-Aphasia Research, Group meetings, spring 2024, Wed 3-4, zoom, Constant Therapy project, group meetings, spring 2024, Wed 1-2, zoom AI for Diagnosing Infant Pneumonia in Resource Limited Settings, spring 2024, Fri 9 am, my zoom room Artificial Intelligence & Emerging Media (AIEM), Open Framing: Interactive ML tool for multilingual media frame analysis of user-provided data. Group meetings, fall 2024, Wed 9-10 EST on zoom (link managed by Ge Gao). Computer Vision for Student Learning with Online Tutors: Weekly meetings, spring 2024, Mon 2-3 pm EST, zoom Pose estimation, spring 2024, Mon 12 noon. My zoom room. Document Image Analysis, Dataset Arabic-9K. Learning to Separate: Detecting Heavily Occluded Object in Urban Scenes, BU TIV: Thermal Infrared Video Benchmark Dataset Visual observation and analysis of bats and their group behavior, using multi-camera videography, Medical imaging, Cell image analysis. Object detection, segmentation, tracking, and recognition Communicating COVID-19, Video of Presentation at CRA Conference 2020 (< 4 min) AI Research Initiative: Seminars, fall 2024, Wed 1-2 pm.
Publications:	Recent publications and full list of publications, Google Scholar profile, Semantic Scholar, ACM Digital Library profile, DBLP profile, https://orcid.org/0000-0002-4491-6868
Students:	Current PhD students: Ge Gao (co-advised with Derry Wijaya), Yiwen Gu, Stan (Sha) Lai, Mahir Patel (co-advised with Bryan Plummer), Wenda Qin, Kaihong Wang, Hao Yu, and Yi Zheng (co-advised with Wijaya Kolachalama). Current MS research students: Sarah Bonner, Alex (Hantian) Liu, and Farid Karimli. Most recently graduated PhD students: Elham Saraee, Ajjen Joshi, Wenxin Feng, Andrew Kurauchi, Mehrnoosh Sameki. UROP students: Alex Lavaee, Junyi Li, Chloe Valcourt, Jialin Yu, Student Awards.
Former Postdocs:	Randa Elanwar and Zheng Wu.
Teaching:	Artificial Intelligence (CS 640) in Fall 2024, Room CGS 516, Tue, Thu 11:00 - 12:15 pm Image and Video Computation (CS 585) in Spring 2024, Room CS 224, Tue/Thu 5-6:15 pm Geometric Algorithms (CS 132) in Fall 2010 Graduate Initiation Seminar (CS 697) in Spring 2018. In Spring 2023: Mon 10:05-10:55, CCDS 701. Directed Study in Image and Video Computing: CAS CS 491, GRS CS 941, or GRS CS 979, or Directed Study in AI: GRS CS 940, ongoing.
Office Hours:	Spring 2023: Mon after class (11:05 - 11:55) in my office CCDS 827 or by arrangement. Zoom link: https://bostonu.zoom.us/my/margritbetke
Honors & Awards:	HERS Leadership Institute Award, Wellesley Class of 2018. Elected to Senior Member of the ACM and Senior Member of the IEEE in October 2012. One of two academics to win the "Top 10 Women to Watch in New England" Award in 2005. Many sponsored students and researchers have won awards.
In the News:	Nov. 10, 2023: 7 Investigates: Voice Cloning. Feb. 2, 2022: ML reveals new factor for predicting a stroke survivor’s ability to regain language skills Can the U.S. win the A.I. arms race? Interview by Futurity, March 4, 2019. Google Award, Group Behavior Award. Camera Mouse: Video Interview, BU, Kablenet, Belfast Telegraph, MassHighTech, Bradford Telegraph & Argus Empathic Painting: BBC, ABC News, SydneyMH, The Hindu, DigitalWorld Tokyo, Inky, Canada TecChannel - München, Frontpage - Netherlands
Free Software:	Camera Mouse - a program that enables a person with severe disabilities to control the mouse pointer on the computer screen just by moving the head (see also research version). Camera Canvas - image editing software developed for people with severe motor impairments who cannot use their hands to operate a mouse or keyboard. It can be used with the Camera Mouse or other mouse-replacement tools. Camera Canvas enables users to edit images and draw pictures just by moving their heads.
Patent:	"Method and system for the detection, comparison and volumetric quantification of pulmonary nodules on medical computed tomography scans." Inventors Margrit Betke and Jane P. Ko., US Patent 7,206,462, issued on April 17, 2007.
Editor:	Associate Editor, Editorial Board of the journal IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Book:

M. Betke and Z. Wu. 2016. Data Association for Multi-Object Visual Tracking. Morgan & Claypool Lecture Series on Computer Vision. 120 pages.

Recent Publications:

Journal Papers:

Umair Khan, Russell Thompson, Jason Li, Lauren P. Etter, Ingrid Camelo, Rachel C. Pieciak, Ilse Castro-Aragon, Bindu Setty, Christopher C. Gill, Libertario Demi, and Margrit Betke. FLUEnT: Transformer for detecting lung consolidations in videos using fused lung ultrasound encodings. Computers in Biology and Medicine. Vol. 180, 2024, 109014, 10 pages, DOI: 10.1016/j.compbiomed.2024.109014.

Lei Guo, Hao Yu, H. Denis Wu, and Margrit Betke. "The Emotional Power of Partisan Media: A Computer Vision Analysis of the 2020 Democratic Party Presidential Primaries." Mass Communication and Society. July 19, 2024. Pages 1-23. DOI: 10.1080/15205436.2024.2370562.

Randa Elanwar and Margrit Betke (2024). Generative adversarial networks for handwriting image generation: A review. The Visual Computer, July 2, 2024. Pages 1-24. DOI: 10.1007/s00371-024-03534-9.

Zheng, Y., Conrad, R. D., Green, E. J., Burks, Betke, M., Bean, J. E., and Kolachalama, V. B. (2024). Graph attention-based fusion of pathology images and gene expression for prediction of cancer survival IEEE Trans Med Imaging. April 28, 2024. 13 pages. DOI: 10.1109/TMI.2024.3386108. PMID: 38587959

Lauren Etter, Margrit Betke, Ingrid Y. Camelo, Christopher J. Gill, Rachel Pieciak, Russell Thompson, Libertario Demi, Umair Khan, Alyse Wheelock, Janet Katanga, Bindu N. Setty, and Ilse Castro-Aragon. "Curated and Annotated Dataset of Lung US Images of Zambian Children with Clinical Pneumonia." Radiology: Artificial Intelligence, 6(2), 6 pages, February 12, 2024. DOI 10.1148/ryai.230147

Peer-reviewed Conference Papers:

Farid Karimli, Hao Yu, Emmanuel Akosah, Srishti Jain, Margrit Betke, and Wenxin Feng. Demonstration of CameraMouse^AI: A Head-Based Mouse-Control System for People with Severe Motor Disabilities. Accepted at ASSET 2024.

Zijian Chen, Maria Varkanitsv, Prakash Ishwar, Janusz Konrad, Margrit Betke, Swathi Kiran, Arachana Venkataraman. LEGNet: A Lesion-aware Edge-based Graph Neural Network for Predicting Post-stroke Aphasia. Accepted at the 7th International Workshop on Machine Learning in Clinical Neuroimaging. Marrakesh, Morocco, October 10, 2024.

Sarah Bonna, Yu-Cheng Huang, Ekaterina Novozhilova, Sejin Paik, Zhengyang Shan, Michelle Yilin Feng, Ge Gao, Yonish Tayal, Rushil Kulkarni, Jialin Yu, Nupur Divekar, Deepti Ghadiyaram, Derry Wijaya, and Margrit Betke. DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model. To be presented at the European Conference on Computer Vision 2024 Workshop "Fairness and ethics towards transparent AI: facing the chalLEnge through model Debiasing" (FAILED), Milano, Italy, September 29, 2024. 16 pages.

Hao Yu, Danielle A Allessio, William Rebelsky, Tom Murray, John J Magee, Ivon Arroyo, Beverly P Woolf, Sarah Adel Bargal, and Margrit Betke (2024). Affect Behavior Prediction: Using Transformers and Timing Information to Make Early Predictions of Student Exercise Outcome. In: Olney, A.M., Chounta, IA., Liu, Z., Santos, O.C., Bittencourt, I.I. (eds) Artificial Intelligence in Education. AIED 2024. Lecture Notes in Computer Science, vol. 14830. Springer, Cham. DOI 10.1007/978-3-031-64299-9_14. Nominated for the Best Paper Award and Best Student Paper Award of the 25th Conference on Artificial Intelligence in Education (AIED 2024, Refice, Brazil, July 8-12). There were 6 nominations for best paper award and four nominations of best student paper, selected from 143 accepted papers.

Ge Gao, Jongin Kim, Sejin Paik, Ekaterina Novozhilova, Yi Liu, Sarah T Bonna, Margrit Betke, and Derry Tanti Wijaya. Enhancing Emotion Prediction in News Headlines: Insights from ChatGPT and Seq2Seq Models for Free-Text Generation. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024, pages 5944-5955, pdf.

Hao Yu, Danielle A. Allessio, Will Lee, William Rebelsky, Frank Sylvia, Tom Murray, John J. Magee, Ivon Arroyo, Beverly P. Woolf, Sarah Adel Bargal, and Margrit Betke. COVES: A Cognitive-Affective Deep Model that Personalizes Math Problem Difficulty in Real Time and Improves Student Engagement with an Online Tutor. MM'23: Proceedings of the 31st ACM International Conference on Multimedia, (ACM MM) Ottawa, Canada, October 29-November 2, 2023. Pages 6152-6160. DOI 10.1145/3581783.3613965

Kaihong Wang, Donghyun Kim, Rogerio Feris, and Margrit Betke. CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation. Proceedings of the International Conference on Computer Vision (ICCV), Paris, France, October 2-6, 2023. 11 pages. pdf

Saurav Chennuri, Sha Lai, Anne Billot, Maria Varkanitsa, Emily J. Braun, Swathi Kiran, Archana Venkataraman, Janusz Konrad, Prakash Ishwar, and Margrit Betke. Fusion Approaches to Predict Post-stroke Aphasia Severity from Multimodal Neuroimaging Data. Proceedings of the International Conference on Computer Vision Workshop on Computer vision for Automated Medical Diagnosis (ICCV CVAMD 2023). Paris, France, October 2, 2023. Pages 2636-2645. pdf.

Wenda Qin, Lauren Etter, Alinani Simukanga, Christopher Gill, and Margrit Betke. Age-constrained Ear Recognition: The EICZA Dataset and SASE Baseline Model. Proceedings of the IEEE International Joint Conference on Biometrics ( IJCB 2023 ), Ljubljana, Slovenia, September 25-28, 2023. Best Poster Award. Paper pdf.

Russell Thompson, Umair Khan, Jason Li, Lauren Etter, Ingrid Camelo, Rachel Pieciak, Ilse Castro-Aragon, Bindu Setty, Christopher Gill, Libertario Demi, and Margrit Betke. Effectiveness of transferring ultrasound deep learning models from adults to pediatrics for frame based pneumonia classification. The Journal of the Acoustical Society of America: 153 (3_supplement), A189-A189 2023. https://doi.org/10.1121/10.0018616. Oral presentation at the International Lung Ultrasound Symposium (ILUS2023), Trento, Italy, 10-12 July, 2023.

Peer-reviewed Conference Abstracts and Short Papers:

Saunak Bhattacharjee, Umair Khan, Russell Thompson, Lauren P. Etter, Ingrid Camelo, Rachel C. Pieciak, Ilse Castro-Aragon, Bindu Setty, Christopher C. Gill, and Margrit Betke. Unveiling bias in AI model training data: Exploring the impact of intrinsic data variability on lung ultrasound video classification models. Oral presentation at the Conference on Machine Intelligence in Medical Imaging (CMIMI), Boston, MA, October 21-22, 2024. Short paper pdf.

Srishti Jain, Umair Khan, Russell Thompson, Lauren P. Etter, Ingrid Camelo, Rachel C. Pieciak, Ilse Castro-Aragon, Bindu Setty, Christopher C. Gill, and Margrit Betke. Comparative Evaluation of Computationally Efficient and Explainable 1D Brightness Profiles From Axial Projections for Lung Ultrasound Frame Classification. Poster presentation at the Conference on Machine Intelligence in Medical Imaging (CMIMI), Boston, MA, October 21-22, 2024. Short paper pdf.

Saunak Bhattacharjee, Umair Khan, Russell Thompson, Lauren P. Etter, Ingrid Camelo, Rachel C. Pieciak, Ilse Castro-Aragon, Bindu Setty, Christopher C. Gill, and Margrit Betke. Comparing Classic to State-of-the-Art Image Features: A Clustering Approach Using Local Binary Patterns and ResNet-18 Features for Lung Ultrasound Video Classification. Poster presentation at the Conference on Machine Intelligence in Medical Imaging (CMIMI), Boston, MA, October 21-22, 2024. Short paper pdf.

Russell Thompson, Umair Khan, Lauren Etter, Ingrid Camelo, Rachel Pieciak, Ilse Castro-Aragon, Bindu Setty, Christopher Gill, Libertario Demi, and Margrit Betke. Anomaly Detection In Pediatric Lung Ultrasound Using Consistency BiGAN. Oral presentation at the International Lung Ultrasound Symposium (ILUS2023), Trento, Italy, 10-12 July, 2023.

Technical Reports:

Kaihong Wang, Donghyun Kim, Rogerio Feris, Kate Saenko, and Margrit Betke. Exploring Consistency in Cross-Domain Transformer for Domain Adaptive Semantic Segmentation. November 2022. 10 pages. https://arxiv.org/abs/2211.14703

Yi Zheng, Rushin H. Gindra, Emily J. Green, Eric J. Burks, Margrit Betke, Jennifer E. Beane, and Vijaya B. Kolachalama. A graph-transformer for whole slide image classification. May 2022. 16 pages. https://arxiv.org/abs/2205.09671

Donghyun Kim, Kaihong Wang, Kate Saenko, Margrit Betke, and Stan Sclaroff. A Unified Framework for Domain Adaptive Pose Estimation. April 2022. 24 pages. https://arxiv.org/abs/2204.00172