Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
HW-MLVQA: Elucidating Multilingual Handwritten Document Understanding with a Comprehensive VQA Benchmark
Aniket Pal, Ajoy Mondal, Minesh Mathew +1
The proliferation of MultiLingual Visual Question Answering (MLVQA) benchmarks augments the capabilities of large language models (LLMs) and multi-modal LLMs, thereby enabling them…
cs.CV2025
Reading Between the Lanes: Text VideoQA on the Road
George Tom, Minesh Mathew, Sergi Garcia +2
Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem,…
cs.CV2024
Towards Deployable OCR models for Indic languages
Minesh Mathew, Ajoy Mondal, CV Jawahar
Recognition of text on word or line images, without the need for sub-word segmentation has become the mainstream of research and development of text recognition for Indian language…