@InProceedings{GeorgeTom2023,
author="George Tom
and Minesh Mathew
and Sergi Garcia Bordils
and Dimosthenis Karatzas
and CV Jawahar",
title="Reading Between the Lanes: Text VideoQA on the Road",
booktitle="17th International Conference on Document Analysis and Recognition",
year="2023",
volume="14192",
pages="137--154",
optkeywords="VideoQA",
optkeywords="scene text",
optkeywords="driving videos",
abstract="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, while textual cues typically appear for a short time span, and early detection at a distance is necessary. Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason over time. To address this issue, we introduce RoadTextVQA, a new dataset for the task of video question answering (VideoQA) in the context of driver assistance. RoadTextVQA consists of 3, 222 driving videos collected from multiple countries, annotated with 10, 500 questions, all based on text or road signs present in the driving videos. We assess the performance of state-of-the-art video question answering models on our RoadTextVQA dataset, highlighting the significant potential for improvement in this domain and the usefulness of the dataset in advancing research on in-vehicle support systems and text-aware multimodal question answering. The dataset is available at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtextvqa.",
optnote="DAG",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3906), last updated on Wed, 17 Jan 2024 15:37:09 +0100",
opturl="https://link.springer.com/chapter/10.1007/978-3-031-41731-3_9$\#$citeas"
}