AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

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

Pengfei Yue, Xingran Zhao, Juntao Chen, Peng Hou, Wang Longchao, Jianghang Lin, Shengchuan Zhang, Anxiang Zeng, Liujuan Cao

CVPR 2026 · Vision-language and multimodal › Visual question answering · approach: Visual reasoning diagnostics · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
evaluate on low-resource scripts (Khmer, Lao, Burmese) instead of EnglishMLLMs on TEC-VQA · SEA-Vision TEC-VQAaccuracy (%): 62.85 -> 8.17 (EN vs MY avg)Hurt
use general MLLM (Gemini2.5-Pro) instead of best expert model dots.ocrdocument parsing · SEA-Vision Document ParsingNED: 0.186 -> 0.159Improved
use specialized pipeline PaddleOCR-VL instead of general MLLMs on high-resource languagesPaddleOCR-VL · SEA-Vision Document Parsing (EN)NED: 0.154 -> 0.108Improved
use Gemini2.5-Pro on low-resource scripts vs PaddleOCR-VLdocument parsing · SEA-Vision Document Parsing (KM)NED: 0.634 -> 0.278Improved
use expert models (dots.ocr) vs general models on fixed-layout pagesdocument parsing · SEA-Vision page types (Academic Paper)NED: dots.ocr 0.141 best on Academic Paper; Gemini 0.123 on MagazineMixed
use closed-source vs open-source MLLMsTEC-VQA · SEA-Vision TEC-VQAaccuracy (%): closed avg 37.49 vs open avg 31.34; best Qwen3-VL-32B 40.14 (open) > Gemini 39.49Mixed
scale to TEC-VQA instead of document parsingMLLMs · SEA-Visionaccuracy / NED: 32.36 avg TEC-VQA accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy