JA‑VG‑VQA‑500 is a 500‑sample subset of the Japanese Visual Genome VQA dataset, licensed CC BY 4.0, used to benchmark EvoVLM‑JP‑v1‑7B.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
520
Hugging Face likes
17
Listed
May 13, 2024
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 316 |
| Jan 2026 | 105 |
| Feb 2026 | 449 |
| Mar 2026 | 592 |
| Apr 2026 | 682 |
| May 2026 | 477 |
| Jun 2026 | 439 |
| Jul 2026 | 332 |
| Aug 2026 | 321 |
| Sep 2026 | 453 |
| Oct 2026 | 624 |
| Nov 2026 | 520 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- JMMMU-ProJMMMU1kJMMMU‑Pro is an image‑based Japanese multimodal benchmark created by generating visual questions with a realistic model and human verification, revealing that current open‑source LMMs perform poorly on it and offering a cost‑effective method for future VQA benchmark development.
- JAMMEvalllm-jp830JAMMEval is a distilled benchmark of seven Japanese VQA datasets, refined with two rounds of human annotation to remove ambiguities and non‑visual questions, delivering reliable evaluation of vision‑language models on multimodal Japanese tasks.
- JA-Multi-Image-VQASakanaAI311JA‑Multi‑Image‑VQA is a dataset of 39 images and 55 Japanese question‑answer pairs for evaluating multi‑image VQA, licensed under Apache 2.0 (except the images).
- JIC-VQAline-corporation134JIC‑VQA is a Japanese Vision‑Language benchmark built from a food/flower/facility/landmark image set, providing multiple‑choice questions per sample with four options closely tied to the labels, all images licensed under CC‑BY or public domain terms.
- JGLUEshunk0313kUpdated JGLUE dataset card and loading script for a Japanese NLP benchmark (created by Yahoo Japan and Waseda University) that covers text classification (MARC‑ja, JCoLA), sentence‑pair classification (JNLI), and QA (JSQuAD, JCommonsenseQA), with releases linked on GitHub and Hugging Face.
- JMMMUJMMMU3kJMMMU is a Japanese multimodal benchmark expanded over tenfold to 1,320 culturally diverse questions (720 culture‑agnostic, 600 culture‑specific) translated by native subject experts, now featuring a public leaderboard.
Resources in similar research fields
pdmocrdataset-part1ndl-lab82OCR learning dataset created for digital material OCR text conversion project.GitHubShared: Visual Data in NLP・Multimodality
pdmocrdataset-part2ndl-lab15OCR learning dataset created in OCR processing program research and development project.GitHubShared: Visual Data in NLP・Multimodality
OCR_Japaneasetanreinama251Japanese OCRGitHubShared: Visual Data in NLP・Multimodality
GazeVQAriken-grp0Dataset for the LREC-COLING 2024 paper A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese QuestionsGitHubShared: Visual Data in NLP・Multimodality
cameraCyberAgentAILab26CAMERA (CyberAgent Multimodal Evaluation for Ad Text GeneRAtion) is the Japanese ad text generation dataset.GitHubShared: Visual Data in NLP・Multimodality
huggingface-datasets_wrimeshunk0315WRIME for huggingface datasetsGitHubShared: Visual Data in NLP・Multimodality