# ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering

arXiv: https://arxiv.org/abs/2606.24602 · HTML: https://mlsanity.com/paper/2606.24602/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 61 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 30 of 44)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023)
- [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [InternVideo2: Scaling Foundation Models for Multimodal Video Understanding](https://mlsanity.com/paper/2403.15377/) (2024)
- [NVILA: Efficient Frontier Visual Language Models](https://mlsanity.com/paper/2412.04468/) (2024)
- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension](https://mlsanity.com/paper/2404.16790/) (2024)
- [mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding](https://mlsanity.com/paper/2409.03420/) (2024)
- [WebSRC: A Dataset for Web-Based Structural Reading Comprehension](https://mlsanity.com/paper/2101.09465/) (2021)
- [On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering](https://mlsanity.com/paper/2002.10215/) (2020)
- [Kwai Keye-VL 1.5 Technical Report](https://mlsanity.com/paper/2509.01563/) (2025)
- [EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering](https://mlsanity.com/paper/2502.07411/) (2025)
- [Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy](https://mlsanity.com/paper/2502.05177/) (2025)

## Built on by (most cited first, 1 of 1)

- [AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking](https://mlsanity.com/paper/2608.26141/) (2026)

## Abstract (arXiv)

Despite remarkable progress in multimodal understanding, current MLLMs still exhibit limitations in video text understanding, particularly when semantics emerge through the integration of temporally distributed textual cues across multiple frames. This perception challenge fundamentally differs from static image text understanding, yet existing datasets fail to capture: the vast majority of questions remain answerable from single frames, inadequately reflecting real-world video text comprehension demands. To address this, we present ViTexQA, a large-scale video-text QA dataset, and FrameThinker for robust multi-frame temporal reasoning. We build ViTexQA via a quality-controlled Chain-of-Thought (CoT) annotation pipeline boosted with temporal constraints; all its QA pairs demand cross-frame text fusion to solve, enforcing true temporal reliance. FrameThinker adopts two-stage training for explicit temporal modeling: CoT-Guided Supervised Fine-Tuning (SFT) generates frame-aware reasoning chains, followed by Temporally-grounded Reinforcement Learning (RL) optimized with multi-frame coherence rewards. Evaluations show our method outperforms SOTA baselines on ViTexQA, lifting ROUGE-L by 6.3%.