Search Results - "Mathew, Minesh"

Asking questions on handwritten document collections by Mathew, Minesh, Gomez, Lluis, Karatzas, Dimosthenis, Jawahar, C. V.

“…This work addresses the problem of Question Answering (QA) on handwritten document collections. Unlike typical QA and Visual Question Answering (VQA)…”
Get full text

RoadText-1K: Text Detection & Recognition Dataset for Driving Videos by Reddy, Sangeeth, Mathew, Minesh, Gomez, Lluis, Rusinol, Marcal, Karatzas, Dimosthenis, Jawahar, C.V.

“…Perceiving text is crucial to understand semantics of outdoor scenes and hence is a critical requirement to build intelligent systems for driver assistance and…”
Get full text

DocVQA: A Dataset for VQA on Document Images by Mathew, Minesh, Karatzas, Dimosthenis, Jawahar, C. V.

“…We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+…”
Get full text

MMBERT: Multimodal BERT Pretraining for Improved Medical VQA by Khare, Yash, Bagal, Viraj, Mathew, Minesh, Devi, Adithi, Priyakumar, U Deva, Jawahar, CV

“…Images in the medical domain are fundamentally different from the general domain images. Consequently, it is infeasible to directly employ general domain…”
Get full text

Watching the News: Towards VideoQA Models that can Read by Jahagirdar, Soumya, Mathew, Minesh, Karatzas, Dimosthenis, Jawahar, C. V.

“…Video Question Answering methods focus on common-sense reasoning and visual cognition of objects or persons and their interactions over time. Current VideoQA…”
Get full text

InfographicVQA by Mathew, Minesh, Bagal, Viraj, Tito, Ruben, Karatzas, Dimosthenis, Valveny, Ernest, Jawahar, C. V.

“…Infographics communicate information using a combination of textual, graphical and visual elements. This work explores the automatic understanding of…”
Get full text

Benchmarking Scene Text Recognition in Devanagari, Telugu and Malayalam by Mathew, Minesh, Jain, Mohit, Jawahar, C. V.

“…Inspired by the success of Deep Learning based approaches to English scene text recognition, we pose and bench-mark scene text recognition for three Indic…”
Get full text

ICDAR 2019 Competition on Scene Text Visual Question Answering by Furkan Biten, Ali, Tito, Ruben, Mafla, Andres, Gomez, Lluis, Rusinol, Marcal, Mathew, Minesh, Jawahar, C.V., Valveny, Ernest, Karatzas, Dimosthenis

“…This paper presents final results of ICDAR 2019 Scene Text Visual Question Answering competition (ST-VQA). ST-VQA introduces an important aspect that is not…”
Get full text

An empirical study of CTC based models for OCR of Indian languages by Mathew, Minesh, Jawahar, CV

“…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…”
Get full text

Understanding Video Scenes through Text: Insights from Text-based Video Question Answering by Jahagirdar, Soumya, Mathew, Minesh, Karatzas, Dimosthenis, Jawahar, C. V

“…Researchers have extensively studied the field of vision and language, discovering that both visual and textual content is crucial for understanding scenes…”
Get full text

Watching the News: Towards VideoQA Models that can Read by Jahagirdar, Soumya, Mathew, Minesh, Karatzas, Dimosthenis, Jawahar, C. V

“…Video Question Answering methods focus on commonsense reasoning and visual cognition of objects or persons and their interactions over time. Current VideoQA…”
Get full text

DocVQA: A Dataset for VQA on Document Images by Mathew, Minesh, Karatzas, Dimosthenis, Jawahar, C. V

“…We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+…”
Get full text

Understanding Video Scenes through Text: Insights from Text-based Video Question Answering by Jahagirdar, Soumya, Mathew, Minesh, Karatzas, Dimosthenis, Jawahar, C. V.

“…Researchers have extensively studied the field of vision and language, discovering that both visual and textual content is crucial for understanding scenes…”
Get full text

Reading Between the Lanes: Text VideoQA on the Road by Tom, George, Mathew, Minesh, Garcia, Sergi, Karatzas, Dimosthenis, Jawahar, C. V

“…Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a…”
Get full text

Improving CNN-RNN Hybrid Networks for Handwriting Recognition by Dutta, Kartik, Krishnan, Praveen, Mathew, Minesh, Jawahar, C.V.

“…The success of deep learning based models have centered around recent architectures and the availability of large scale annotated data. In this work, we…”
Get full text

Unconstrained OCR for Urdu Using Deep CNN-RNN Hybrid Networks by Jain, Mohit, Mathew, Minesh, Jawahar, C.V.

“…Building robust text recognition systems for languages with cursive scripts like Urdu has always been challenging. Intricacies of the script and the absence of…”
Get full text

Benchmarking Scene Text Recognition in Devanagari, Telugu and Malayalam by Mathew, Minesh, Jain, Mohit, Jawahar, CV

“…Inspired by the success of Deep Learning based approaches to English scene text recognition, we pose and benchmark scene text recognition for three Indic…”
Get full text

Towards Spotting and Recognition of Handwritten Words in Indic Scripts by Dutta, Kartik, Krishnan, Praveen, Mathew, Minesh, Jawahar, C.V.

“…Handwriting recognition (HWR) in Indic scripts is a challenging problem due to the inherent subtleties in the scripts, cursive nature of the handwriting and…”
Get full text

Offline Handwriting Recognition on Devanagari Using a New Benchmark Dataset by Dutta, Kartik, Krishnan, Praveen, Mathew, Minesh, Jawahar, C.V.

“…Handwriting recognition (HWR) in Indic scripts, like Devanagari is very challenging due to the subtleties in the scripts, variations in rendering and the…”
Get full text

ICDAR 2021 Competition on Document VisualQuestion Answering by Tito, Rubèn, Mathew, Minesh, Jawahar, C. V, Valveny, Ernest, Karatzas, Dimosthenis

“…In this report we present results of the ICDAR 2021 edition of the Document Visual Question Challenges. This edition complements the previous tasks on Single…”
Get full text