Minesh Mathew
മിനേഷ് മാത്യു · ML/CV Researcher
Bangalore, India
I am a senior machine learning scientist at Wadhwani AI, where I lead the ML team for Oral Reading Fluency (ORF). ORF is deployed in multiple states in India and millions of students are assessed for reading fluency. I have completed MS + PhD from IIIT Hyderabad. I obtained my undergraduate degree in B.Tech Computer Science Engineering from NIT Warangal.
My PhD thesis deals with machine-understanding of document images. Specifically, I worked on problems such as OCR in Indian languages, scene text understanding, and Document Visual Question Answering (DocVQA).
News & Updates
- Dec 2025Promoted to senior machine learning scientist at Wadhwani AI.
- Jun 2025Received CVPR 2025 outstanding reviewer award.
- May 2023Received CVPR 2023 outstanding reviewer award
- Apr 2023ICDAR 2023 Challenge on Road text detection, tracking and recognition comes to an end. Results are public now.
- Apr 2023George's work on VQA for driving videos accepted at ICDAR 2023.
- Jan 2023Organizing two challenges in ICDAR 2023: RoadText Video Text Detection, Tracking and Recognition; Text-based Video Question Answering on News Videos.
- Sep 2022Soumya's work on VQA accepted to WACV 2023.
- May 2022Work comparing CTC based architectures for Indian languages OCR on arXiv.
- Mar 2022"Read while you Drive — Multilingual Text Tracking on the Road" accepted to DAS 2022. Congrats Sergi and George.
- Oct 2021Attended ICCV 2021 Doctoral Consortium.
- Oct 2021InfographicVQA paper accepted at WACV 2022.
- Sep 2021Presented work on QA over handwritten documents (oral) at ICDAR 2021.
- Sep 2021Organized first edition of DocVQA workshop at ICDAR.
Academic Services
- Reviewer for conferences — CVPR 2022–2026, NeurIPS 2026, ACCV 2022, ECCV 2022, SIGGRAPH 2022, ICDAR 2021, WACV 2021–2023, ICCV 2021, 2023, 2025
- Reviewer for journals — Pattern Recognition, IEEE TNNLS, TPAMI, Visual Computer, Concurrency and Computation, IJCV, TMLR
- [2023] Organizer, NewsVideo QA and Road-text challenges in ICDAR 2023
- [2021] Organizer, Document Visual Question Answering Workshop, ICDAR 2021
- [2021] Organizer, DocVQA competition, ICDAR 2021
- [2020] Organizer, DocVQA competition, CVPR 2020
- [2020] Organizer and Competition Chair, Text and Documents Workshop, CVPR 2020
- [2019] Organizer, Scene Text VQA Competition, ICDAR 2019
Achievements & Recognitions
- [2025] Outstanding reviewer — CVPR 2025
- [2023] Outstanding reviewer — CVPR 2023
- [2021] Outstanding reviewer (top 5%) — ICCV 2021
- [2021] Selected for WACV 2021 and ICCV 2021 doctoral consortiums
- [2017] Best Paper — Int'l Workshop on Arabic Script Analysis and Recognition (ASAR)
- [2015] Runner up — Microsoft Azure ML Hackathon held at IIIT Hyderabad
- [2015] TCS PhD fellowship