SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia

• URL: http://arxiv.org/abs/2603.15409v1
• Date: Mon, 16 Mar 2026 15:21:12 GMT
• Title: SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia
• Abstract summary: We introduce SEA-Vision, a benchmark that jointly evaluates Document Parsing and Text-Centric Visual Question Answering (TEC-VQA) across 11 Southeast Asian languages.<n>SEA-Vision contains 15,234 document parsing pages from nine representative document types, annotated with hierarchical page-, block-, and line-level labels.<n>It also provides 7,496 TEC-VQA question-answer pairs that probe text recognition, numerical calculation, comparative analysis, logical reasoning, and spatial understanding.
• Score: 40.4434142867308
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on high-resource languages and fail to evaluate models in realistic multilingual environments. In Southeast Asia, the diversity of languages, complex writing systems, and highly varied document types make this challenge even greater. We introduce SEA-Vision, a benchmark that jointly evaluates Document Parsing and Text-Centric Visual Question Answering (TEC-VQA) across 11 Southeast Asian languages. SEA-Vision contains 15,234 document parsing pages from nine representative document types, annotated with hierarchical page-, block-, and line-level labels. It also provides 7,496 TEC-VQA question-answer pairs that probe text recognition, numerical calculation, comparative analysis, logical reasoning, and spatial understanding. To make such multilingual, multi-task annotation feasible, we design a hybrid pipeline for Document Parsing and TEC-VQA. It combines automated filtering and scoring with MLLM-assisted labeling and lightweight native-speaker verification, greatly reducing manual labeling while maintaining high quality. We evaluate several leading multimodal models and observe pronounced performance degradation on low-resource Southeast Asian languages, highlighting substantial remaining gaps in multilingual document and scene text understanding. We believe SEA-Vision will help drive global progress in document and scene text understanding.

Related papers

• JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding [19.312383956707396]
  JaWildText is a diagnostic benchmark for evaluating vision-language models (VLMs) on Japanese scene text understanding.<n>It contains 3,241 instances from 2,961 images newly captured in Japan, with 1.12 million annotated characters spanning 3,643 unique character types.<n>It comprises three complementary tasks that vary in visual organization, output format, and writing style.
  arXiv  Detail & Related papers  (2026-03-30T01:36:16Z)
• EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams [0.8399688944263844]
  EuraGovExam is a benchmark sourced from real-world civil service examinations across five representative Eurasian regions.<n>The dataset contains over 8,000 high-resolution scanned multiple-choice questions covering 17 diverse academic and administrative domains.<n>It also supports practical applications in e-governance, public-sector document analysis, and equitable exam preparation.
  arXiv  Detail & Related papers  (2026-03-28T10:29:51Z)
• DISCO: Document Intelligence Suite for COmparative Evaluation [1.4425299138308667]
  Document intelligence requires accurate text extraction and reliable reasoning over document content.<n>We evaluate optical character recognition (OCR) pipelines and vision-language models (VLMs) separately on parsing and question answering across diverse document types.
  arXiv  Detail & Related papers  (2026-03-04T14:47:34Z)
• VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding [49.07705729597171]
  VisR-Bench is a benchmark for question-driven multimodal retrieval in long documents.<n>Our benchmark comprises over 35K high-quality QA pairs across 1.2K documents.<n>We evaluate various retrieval models, including text-based methods, multimodal encoders, and MLLMs.
  arXiv  Detail & Related papers  (2025-08-10T21:44:43Z)
• MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks [56.350173737493215]
  Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency.<n>MMESGBench is a first-of-its-kind benchmark dataset to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents.<n>MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories.
  arXiv  Detail & Related papers  (2025-07-25T03:58:07Z)
• DRISHTIKON: Visual Grounding at Multiple Granularities in Documents [21.376466879737855]
  DRISHTIKON is a multi-granular and multi-block visual grounding framework.<n>Our approach integrates multilingual OCR, large language models, and a novel region matching algorithm to localize answer spans.<n>Our findings pave the way for more robust and interpretable document understanding systems.
  arXiv  Detail & Related papers  (2025-06-26T14:32:23Z)
• Parrot: Multilingual Visual Instruction Tuning [66.65963606552839]
  Existing methods typically align vision encoders with Multimodal Large Language Models (MLLMs) via supervised fine-tuning (SFT)<n>We propose PARROT, a novel approach that leverages textual guidance for visual token alignment at the language level.<n>We introduce the Massive Multilingual Multimodal Benchmark (MMMB), a new benchmark comprising 6 languages, 15 categories, and 12,000 questions.
  arXiv  Detail & Related papers  (2024-06-04T17:56:28Z)
• MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering [57.30218240464696]
  We introduce MTVQA, the first benchmark featuring high-quality human expert annotations across 9 diverse languages.<n>MTVQA is the first benchmark featuring high-quality human expert annotations across 9 diverse languages.
  arXiv  Detail & Related papers  (2024-05-20T12:35:01Z)
• OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models [122.27878464009181]
  We conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available.
  arXiv  Detail & Related papers  (2023-05-13T11:28:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.