# RoadText-1K: Text Detection & Recognition Dataset for Driving Videos

arXiv: https://arxiv.org/abs/2005.09496 · HTML: https://mlsanity.com/paper/2005.09496/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2020.

## Built on by (most cited first, 25 of 25)

- [A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension](https://mlsanity.com/paper/2305.03347/) (2023)
- [A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer](https://mlsanity.com/paper/2112.04888/) (2021)
- [Reading Between the Lanes: Text VideoQA on the Road](https://mlsanity.com/paper/2307.03948/) (2023)
- [End-to-End Video Text Spotting with Transformer](https://mlsanity.com/paper/2203.10539/) (2022)
- [MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios](https://mlsanity.com/paper/2505.21333/) (2025)
- [Scalable Mask Annotation for Video Text Spotting](https://mlsanity.com/paper/2305.01443/) (2023)
- [When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding](https://mlsanity.com/paper/2506.05551/) (2025)
- [VidText: Towards Comprehensive Evaluation for Video Text Understanding](https://mlsanity.com/paper/2505.22810/) (2025)
- [Video Text Tracking With a Spatio-Temporal Complementary Model](https://mlsanity.com/paper/2111.04987/) (2021)
- [Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation](https://mlsanity.com/paper/2103.14496/) (2021)
- [ICDAR 2023 Video Text Reading Competition for Dense and Small Text](https://mlsanity.com/paper/2304.04376/) (2023)
- [DSText V2: A Comprehensive Video Text Spotting Dataset for Dense and Small Text](https://mlsanity.com/paper/2312.01938/) (2023)
- [Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study](https://mlsanity.com/paper/2412.20613/) (2024)
- [Transfer Learning for Scene Text Recognition in Indian Languages](https://mlsanity.com/paper/2201.03180/) (2022)
- [PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2311.17955/) (2023)
- [PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer](https://mlsanity.com/paper/2308.15004/) (2023)
- [STEP -- Towards Structured Scene-Text Spotting](https://mlsanity.com/paper/2309.02356/) (2023)
- [Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes](https://mlsanity.com/paper/2310.00558/) (2023)
- [Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models](https://mlsanity.com/paper/2512.11899/) (2025)
- [Policy-based Foveated Imaging and Perception](https://mlsanity.com/paper/2606.02565/) (2026)
- [Video text tracking for dense and small text based on pp-yoloe-r and sort algorithm](https://mlsanity.com/paper/2304.00018/) (2023)
- [LOGO: Video Text Spotting with Language Collaboration and Glyph Perception Model](https://mlsanity.com/paper/2405.19194/) (2024)
- [ClapperText: A Benchmark for Text Recognition in Low-Resource Archival Documents](https://mlsanity.com/paper/2510.15557/) (2025)
- [TraRA: Trajectory-level Recognition Aggregation for Video Text Spotting in Urban Surveillance](https://mlsanity.com/paper/2606.07161/) (2026)
- [Back-Tracking from Clarity: Self-Learning to See Text from Afar](https://mlsanity.com/paper/2609.32477/) (2026)

## Abstract (arXiv)

Perceiving text is crucial to understand semantics of outdoor scenes and hence is a critical requirement to build intelligent systems for driver assistance and self-driving. Most of the existing datasets for text detection and recognition comprise still images and are mostly compiled keeping text in mind. This paper introduces a new "RoadText-1K" dataset for text in driving videos. The dataset is 20 times larger than the existing largest dataset for text in videos. Our dataset comprises 1000 video clips of driving without any bias towards text and with annotations for text bounding boxes and transcriptions in every frame. State of the art methods for text detection, recognition and tracking are evaluated on the new dataset and the results signify the challenges in unconstrained driving videos compared to existing datasets. This suggests that RoadText-1K is suited for research and development of reading systems, robust enough to be incorporated into more complex downstream tasks like driver assistance and self-driving. The dataset can be found at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtext-1k