avatar

(Istiak) Hossain Shihab

Ph.D. Student
Oregon State University
istiak (at) proton.me


About Me

I am a Ph.D. student at Oregon State University, set to begin my studies in the Fall of 2023. As a researcher, my current focus revolves around delving deeply into the interpretability of machine learning models and multimodal learning.

I am a machine learning researcher with experience in natural language processing, speech recognition, and document layout recognition. Additionally, I possess several years of industry experience in backend development of products with 70M+ users. I have authored several papers that have undergone peer review and been published in esteemed conferences and journals such as ICDAR, InterSpeech, CVPR Workshop, and Briefings in Bioinformatics. Furthermore, I have actively participated and organized in various competitions and challenges related to my research interests.

Research Interests

News

Publications

  1. ICDAR
    BaDLAD: Large Multi-Domain Bengali Document Layout Analysis Dataset
    Md Istiak Hossain Shihab, M Hasan, MR Emon, SM Hossen, M Ansary, I Ahmed, FR Rakib, SE Dhruvo, SS Dip, AH Pavel, MH Meghla, M Haque, SS Chowdhury, F Sadeque, T Reasat, AI Humayun, AS Sushmit
    The 17th International Conference on Document Analysis and Recognition (ICDAR), 2023.
    PDF Oral Presentation

  2. INTERSPEECH
    OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking
    FR Rakib, SS Dip, S Alam, N Tasnim, Md Istiak Hossain Shihab, MN Ansary, SM Hossen, MH Meghla, M Mamun, F Sadeque, SS Chowdhury, T Reasat, AS Sushmit, AI Humayun.
    Interspeech, 2023.
    PDF Oral Presentation

  3. ARXIV
    Bornil: An open-source sign language data crowdsourcing platform for AI enabled dialect-agnostic communication
    SE Dhruvo, MA Rahman, MK Mandal, Md Istiak Hossain Shihab, AA Ansary, KF Shithi, S Khanom, R Akter, SH Arib, MN Ansary, S Mehnaz, R Sultana, S Rahman, SS Chowdhury, SA Chowdhury, F Sadeque, AS Sushmit
    Arxiv, 2023.
    PDF

  4. ARXIV
    bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documents
    IM Zulkarnain, SB Islam, MZAZ Farabe, MMH Shawon, JM Abedin, BR Hasan, M Haque, Md Istiak Hossain Shihab, S Mobassir, MD Ansary, AS Sushmit, F Sadeque
    Arxiv, 2023.
    PDF

  5. CVPRW
    VISTA: Vision transformer enhanced by U-Net and image colorfulness frame filtration for automatic retail checkout
    Md Istiak Hossain Shihab, N Tasnim, H Zunair, LK Rupty, N Mohammed
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022.
    PDF Code 3rd Best Solution

  6. SemEval
    TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla
    Md Istiak Hossain Shihab, N Tasnim, AS Sushmit, S Bethard, F Sadeque
    Proceedings of the 16th International Workshop on Semantic Evaluation, 2022
    PDF

  7. FLAIRS
    Observing the Unobserved: A Newspaper Based Dengue Surveillance System for the Low-Income Regions of Bangladesh
    Md Istiak Hossain Shihab, N Tasnim, M Rahman, JR Saurav, SR Islam, MR Amin.
    The International FLAIRS Conference Proceedings 34, 2021
    PDF

  8. KDDW
    Exploring the Scope and Potential of Local Newspaper-based Dengue Surveillance in Bangladesh
    Md Istiak Hossain Shihab, N Tasnim, M Rahman, SR Islam, MR Amin.
    Joint KDD 2021 Health Day and 2021 KDD Workshop on Applied Data Science for Healthcare, 2021.
    PDF Code Oral Presentation

  9. BIB
    Choice of assemblers has a critical impact on de novo assembly of SARS-CoV-2 genome and characterizing variants
    R Islam, RS Raju, N Tasnim, Md Istiak Hossain Shihab, MA Bhuiyan, Y Araf, T Islam.
    Briefings in bioinformatics, 2021.
    PDF