Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
publications
Design of a gesture controlled robotic gripper arm using neural networks
Published in IEEE ICPCSI, 2017
A neural network-based design for a gesture-controlled robotic gripper arm.
Recommended citation: Sushmit, A., Haque, F. M., Shahriar, M., …, Sarkar, M. R. (2017). "Design of a gesture controlled robotic gripper arm using neural networks." IEEE ICPCSI.
Download Paper
Design of a voice controlled robotic gripper arm using neural networks
Published in IEEE ICECDS, 2017
A neural network-driven voice controlled robotic gripper arm design.
Recommended citation: Haque, F. M., Sushmit, A., Sarkar, M. R. (2017). "Design of a voice controlled robotic gripper arm using neural networks." IEEE ICECDS.
Download Paper
A pipeline for lung tumor detection and segmentation from CT scans using dilated convolutional neural networks
Published in IEEE ICASSP, 2019
A deep learning pipeline for lung tumor detection and segmentation using dilated convolutional neural networks on CT scans.
Recommended citation: Hossain, S., Najeeb, S., Sushmit, A. S., … (2019). "A pipeline for lung tumor detection and segmentation from CT scans using dilated convolutional neural networks." IEEE ICASSP.
Download Paper
End-to-end sleep staging with raw single channel EEG using deep residual convnets
Published in IEEE EMBS BHI, 2020
Deep residual convolutional networks for end-to-end sleep staging using raw single-channel EEG.
Recommended citation: Humayun, A. I., Sushmit, A., Hasan, T., Bhuiyan, M. I. H., … (2020). "End-to-end sleep staging with raw single channel EEG using deep residual convnets." IEEE EMBS BHI.
Download Paper
A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes
Published in arXiv, 2020
A large multi-target Bengali handwritten grapheme dataset for low-resource OCR and handwriting recognition research.
Recommended citation: Alam, S., Reasat, T., Sushmit, A., … (2020). "A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes." arXiv.
Download Paper
Segcodenet: Color-coded segmentation masks for activity detection from wearable cameras
Published in CVPR Workshop, 2020
A segmentation dataset for activity detection using wearable camera footage.
Recommended citation: Sushmit, A., Ghosh, P., Istiak, M. A., Rashid, N., Akash, A. H., Hasan, T. (2020). "Segcodenet: Color-coded segmentation masks for activity detection from wearable cameras." CVPR Workshop.
Download Paper
Privacy-aware activity classification from first person office videos
Published in ECCV Workshop, 2020
Activity classification in office videos with explicit privacy-aware design.
Recommended citation: Ghosh, P., Istiak, M. A., Rashid, N., Akash, A. H., …, Sushmit, A., Hasan, T. (2020). "Privacy-aware activity classification from first person office videos." ECCV Workshop.
Download Paper
Multi-label classification of common Bengali handwritten graphemes: Dataset and challenge
Published in arXiv, 2020
A dataset and competition challenge for multi-label classification of Bengali handwritten graphemes.
Recommended citation: Alam, S., Reasat, T., Sushmit, A., … (2020). "Multi-label classification of common Bengali handwritten graphemes: Dataset and challenge." arXiv.
Download Paper
TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla
Published in SemEval, 2022
A SemEval team paper on Bangla named entity recognition using augmentation and model ensembles.
Recommended citation: Tasnim, N., Shihab, M. I., Sushmit, A., Bethard, S., Sadeque, F. (2022). "TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla." SemEval.
Download Paper
Bengali Common Voice speech dataset for automatic speech recognition
Published in arXiv, 2022
A large Bengali Common Voice speech dataset for automatic speech recognition research.
Recommended citation: Alam, S., Sushmit, A., Abdullah, Z., … (2022). "Bengali Common Voice speech dataset for automatic speech recognition." arXiv.
Download Paper
Cardiac CT motion artifact grading via semi-automatic labeling and vessel tracking using synthetic image-augmented training data
Published in Journal of X-Ray Science and Technology, 2022
A method for grading motion artifacts in cardiac CT using synthetic image augmentation and vessel tracking.
Recommended citation: Xu, Y., Sushmit, A., Lyu, Q., …, Yu, H. (2022). "Cardiac CT motion artifact grading via semi-automatic labeling and vessel tracking using synthetic image-augmented training data." Journal of X-Ray Science and Technology.
Download Paper
bbocr: An open-source multi-domain OCR pipeline for Bengali documents
Published in Open Source, 2022
An open-source multi-domain OCR pipeline tailored for Bengali documents.
Recommended citation: Zulkarnain, I. M., Islam, S. B., …, Sushmit, A. (2022). "bbocr: An open-source multi-domain OCR pipeline for Bengali documents." Open Source.
Download Paper
Bornil: An open-source sign language data crowdsourcing platform for AI enabled dialect-agnostic communication
Published in HCI, 2023
An open-source crowdsourcing platform to collect sign language data for dialect-agnostic AI communication.
Recommended citation: Dhruvo, S. E., Rahman, M. A., …, Sushmit, A. (2023). "Bornil: An open-source sign language data crowdsourcing platform for AI enabled dialect-agnostic communication." HCI.
Download Paper
OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking
Published in Interspeech, 2023
A Bengali speech recognition dataset designed for out-of-distribution benchmarking.
Recommended citation: Dip, S. S., Alam, S., Tasnim, N., …, Sushmit, A. (2023). "OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking." Interspeech.
Download Paper
Badlad: A large multi-domain Bengali document layout analysis dataset
Published in ICDAR, 2023
A large multi-domain Bengali document layout analysis dataset for OCR and document understanding.
Recommended citation: Hossain Shihab, M. I., Hasan, M. R., …, Sushmit, A. (2023). "Badlad: A large multi-domain Bengali document layout analysis dataset." ICDAR.
Download Paper
X-ray image compression using convolutional recurrent neural networks
Published in IEEE EMBS BHI, 2023
A convolutional recurrent neural network approach for medical X-ray image compression.
Recommended citation: Sushmit, A., Zaman, S. U., Humayun, A. I., Hasan, T., Bhuiyan, M. I. H., … (2023). "X-ray image compression using convolutional recurrent neural networks." IEEE EMBS BHI.
Download Paper
X-ray image compression using convolutional recurrent neural networks
Published in IEEE EMBS BHI, 2023
A convolutional recurrent neural network approach for X-ray image compression.
Recommended citation: Sushmit, A., Zaman, S. U., Humayun, A. I., Hasan, T., Bhuiyan, M. I. H., … (2023). "X-ray image compression using convolutional recurrent neural networks." IEEE EMBS BHI.
Download Paper
Unicode normalization and grapheme parsing of Indic languages
Published in LREC-COLING, 2023
Unicode normalization and grapheme parsing techniques for Indic languages.
Recommended citation: Ansary, M. N., Adib, Q. A. R., …, Sushmit, A. (2023). "Unicode normalization and grapheme parsing of Indic languages." LREC-COLING.
Download Paper
Mapping violence: Developing an extensive framework to build a Bangla sectarian expression dataset from social media interactions
Published in ACL, 2023
A framework to construct a Bangla sectarian expression dataset from social media interactions.
Recommended citation: Tasnim, N., Gupta, S. S., …, Sushmit, A. (2023). "Mapping violence: Developing an extensive framework to build a Bangla sectarian expression dataset from social media interactions." ACL.
Download Paper
Data efficient contrastive learning in histopathology using active sampling
Published in MICCAI Workshop, 2024
Active sampling for data-efficient contrastive learning in histopathology.
Recommended citation: Reasat, T., Sushmit, A., Smith, D. S. (2024). "Data efficient contrastive learning in histopathology using active sampling." MICCAI Workshop.
Download Paper
Towards Santali linguistic inclusion: Building the first Santali-to-English translation model using mT5 Transformer and data augmentation
Published in ACL Workshop, 2024
The first Santali-to-English translation model built with mT5 and data augmentation.
Recommended citation: Billah, S. M. M., Subarna, A. A., …, Sushmit, A. (2024). "Towards Santali linguistic inclusion: Building the first Santali-to-English translation model using mT5 Transformer and data augmentation." ACL Workshop.
Download Paper
IPA transcription of Bengali texts
Published in Speech and Language, 2024
IPA transcription tools and evaluation for Bengali text data.
Recommended citation: Fatema, K., Haider, F. D., …, Sushmit, A. (2024). "IPA transcription of Bengali texts." Speech and Language.
Download Paper
A data generation pipeline for cardiac vessel segmentation and motion artifact grading
Published in Medical Imaging, 2024
A data generation pipeline for cardiac vessel segmentation and motion artifact grading.
Recommended citation: Sushmit, A., Xu, Y., Mariani, O., …, Yu, H. (2024). "A data generation pipeline for cardiac vessel segmentation and motion artifact grading." Medical Imaging.
Download Paper
RegSpeech12: A regional corpus of Bengali spontaneous speech across dialects
Published in Linguistics, 2024
A regional corpus of Bengali spontaneous speech collected across dialects.
Recommended citation: Hassan, M. R., Hossain, A., …, Sushmit, A. (2024). "RegSpeech12: A regional corpus of Bengali spontaneous speech across dialects." Linguistics.
Download Paper
A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes
Published in ICDAR, 2024
A large multi-target Bengali handwritten grapheme dataset for low-resource OCR and script recognition research.
Recommended citation: Alam, S., Reasat, T., Sushmit, A., … (2024). "A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes." ICDAR.
Download Paper
Abugida normalizer and parser for Unicode texts
Published in Software/Toolkit, 2025
An Abugida normalizer and parser for Unicode texts across Indic scripts.
Recommended citation: Ansary, M. N., Adib, Q. A. R., …, Sushmit, A. (2025). "Abugida normalizer and parser for Unicode texts." Software/Toolkit.
Download Paper
BanglaDocAtlas: A Multi-Class Annotated Dataset for Complex Bangla Document Layout Analysis
Published in Document Analysis, 2025
A multi-class annotated dataset for complex Bangla document layout analysis.
Recommended citation: Hossain, M. S., Ferdous, J., …, Sushmit, A. (2025). "BanglaDocAtlas: A Multi-Class Annotated Dataset for Complex Bangla Document Layout Analysis." Document Analysis.
Download Paper
talks
Champion, National Robotics Competition 2017
Published:
Champion in the National Robotics Competition 2017 for a machine learning solution.
Champion, National Power Energy Hackathon 2017
Published:
Champion of the National Power Energy Hackathon 2017 (‘BUET Luminaries’) for a smart grid system with SCADA integration.
Runner-up, Bangladesh Physics Olympiad
Published:
Runner-up in the Bangladesh Physics Olympiad.
Runner-up, Bangladesh National Science Olympiad
Published:
Runner-up in the Bangladesh National Science Olympiad.
Workshop: Matlab and Image Processing
Published:
A six-day hands-on workshop on image processing and deep learning, teaching practical Matlab workflows and AI methods to university students.
Public Lecture: Workshop on Basic Matlab and Image Processing
Published:
Public lecture and workshop at BUET on basic Matlab and image processing, introducing practical workflows and techniques for university students.
Champion, IEEE VIP CUP 2018
Published:
Champion at IEEE VIP CUP 2018, presenting at ICIP 2018 in Greece on a 3D CT lung tumor detection and segmentation pipeline.
Runner-up, IEEE VIP CUP 2019
Published:
Runner-up at IEEE VIP CUP 2019 while coaching the BUET Synapticans and tutoring six undergraduate students on a privacy-aware activity classification system using first-person video.
NVIDIA Titan Xp GPU Grant
Published:
Awarded an NVIDIA Titan Xp GPU through the NVIDIA GPU Grant program to support data science research and experimentation.
Runner-up, Call for Nation Covid Accelerator
Published:
Runner-up in the Call for Nation Covid Accelerator competition for RadAssist, Bangladesh’s first AI-assisted teleradiology platform.
Bengali Language Technology Roadmap
Published:
A conference presentation on Bengali language technology history, research challenges, and an inclusive roadmap for regional AI development.
Guest Lecture: Introduction to Data Science
Published:
Guest lecture and course design support for SWE 227 Introduction to Data Science, covering core concepts in data science, model evaluation, and practical applications.
Public Lecture: Demystifying AI
Published:
A public lecture on demystifying artificial intelligence, covering AI ethics, applied machine learning, and implications for policy and society in Bangladesh.
Launch of the National Grammatical Error Detection (GED) Competition
Published:
Launched the national Grammatical Error Detection competition on Kaggle, serving as host, data curator, judge, and providing bias analysis and feedback to top national research teams.
Kaggle Best Community Competition Award
Published:
Awarded Kaggle Best Community Competition Award for organizing the DL Sprint competition on Bengali Automatic Speech Recognition with 59 participating teams.
Host, National ASR Hackathon
Published:
Hosted the National ASR Hackathon organized by Bengali.AI and BUET CSE, serving as host, data curator, and judge.
Selected Delegate, ITU-T AI Capacity Building Workshop
Published:
Selected as a delegate for an ITU-T AI capacity building workshop, engaging regulators and ministry officials on AI ethics, risk governance, and integrating ITU-T recommendations into national digital strategy.
teaching
Coordinator, Bengali.AI
Research Leadership and Mentorship, Bengali.AI, 2020
Coordinated community-driven AI research initiatives, launched large-scale Bengali datasets and competitions, crowdsourced speech and sign language corpora, and mentored emerging researchers on dataset creation, annotation protocols, and reproducible research workflows.
VC Fellow and Lecturer
University teaching, Brac University, Department of Computer Science and Engineering, 2021
Taught courses in Artificial Intelligence, Complex Variables & Laplace Transformations, and Numerical Analysis. Supervised research, graded coursework, and provided student consultation and academic support.
Graduate Research & Teaching Assistant
Graduate teaching assistantship, Rensselaer Polytechnic Institute, Biomedical Engineering, 2021
Supported undergraduate and graduate teaching activities in biomedical imaging, including lab sessions, grading, academic mentoring, and collaborative research supervision.
Technical Trainer
Government capacity building, Bangladesh Korea Institute of Information & Communication Technology (BKIICT), Bangladesh Computer Council, 2026
Delivered public-sector capacity building to over 300 government officials on national digital policy, system interoperability, ICT ordinance implementation, and regulatory framework adoption. Designed and delivered a course on Data Analytics and Data-Driven Decision Making covering data collection methodologies, statistical analysis, and real-time visualization. Instructed public-sector professionals on cybersecurity, personal data protection, and digital hygiene to strengthen institutional risk posture. Fostered strategic data literacy by teaching participants to evaluate data source integrity, challenge operational assumptions, and translate evidence into organizational decisions.