{"url":"/dataset/iglue","name":"IGLUE","full_name":"Image-Grounded Language Understanding Evaluation","description_markdown":"The **Image-Grounded Language Understanding Evaluation** (**IGLUE**) benchmark brings together—by both aggregating pre-existing datasets and creating new ones—visual question answering, cross-modal retrieval, grounded reasoning, and grounded entailment tasks across 20 diverse languages. The benchmark enables the evaluation of multilingual multimodal models for transfer learning, not only in a zero-shot setting, but also in newly defined few-shot learning setups.","description_withheld":null,"homepage":"https://iglue-benchmark.github.io/","introduced_date":"2022-01-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/iglue-a-benchmark-for-transfer-learning","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","first_author":"Emanuele Bugliarello","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Reasoning","url":"/task/visual-reasoning","datasets_with_task":"/datasets/task/visual-reasoning"},{"name":"Zero-Shot Cross-Lingual Transfer","url":"/task/zero-shot-cross-lingual-transfer","datasets_with_task":"/datasets/task/zero-shot-cross-lingual-transfer"},{"name":"Zero-Shot Cross-Lingual Text-to-Image Retrieval","url":"/task/zero-shot-cross-lingual-text-to-image","datasets_with_task":"/datasets/task/zero-shot-cross-lingual-text-to-image"},{"name":"Zero-Shot Cross-Lingual Image-to-Text Retrieval","url":"/task/zero-shot-cross-lingual-image-to-text","datasets_with_task":"/datasets/task/zero-shot-cross-lingual-image-to-text"},{"name":"Zero-Shot Cross-Lingual Visual Natural Language Inference","url":"/task/zero-shot-cross-lingual-visual-natural","datasets_with_task":"/datasets/task/zero-shot-cross-lingual-visual-natural"},{"name":"Zero-Shot Cross-Lingual Visual Reasoning","url":"/task/zero-shot-cross-lingual-visual-reasoning","datasets_with_task":"/datasets/task/zero-shot-cross-lingual-visual-reasoning"},{"name":"Zero-Shot Cross-Lingual Visual Question Answering","url":"/task/zero-shot-cross-lingual-visual-question","datasets_with_task":"/datasets/task/zero-shot-cross-lingual-visual-question"},{"name":"Max-Shot Cross-Lingual Visual Natural Language Inference","url":"/task/max-shot-cross-lingual-visual-natural","datasets_with_task":"/datasets/task/max-shot-cross-lingual-visual-natural"},{"name":"Max-Shot Cross-Lingual Visual Question Answering","url":"/task/max-shot-cross-lingual-visual-question","datasets_with_task":"/datasets/task/max-shot-cross-lingual-visual-question"},{"name":"Max-Shot Cross-Lingual Visual Reasoning","url":"/task/max-shot-cross-lingual-visual-reasoning","datasets_with_task":"/datasets/task/max-shot-cross-lingual-visual-reasoning"},{"name":"Max-Shot Cross-Lingual Text-to-Image Retrieval","url":"/task/max-shot-cross-lingual-text-to-image","datasets_with_task":"/datasets/task/max-shot-cross-lingual-text-to-image"},{"name":"Max-Shot Cross-Lingual Image-to-Text Retrieval","url":"/task/max-shot-cross-lingual-image-to-text","datasets_with_task":"/datasets/task/max-shot-cross-lingual-image-to-text"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Bengali","url":"/datasets/language/bengali"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Bulgarian","url":"/datasets/language/bulgarian"},{"name":"Danish","url":"/datasets/language/danish"},{"name":"Estonian","url":"/datasets/language/estonian"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"},{"name":"Greek","url":"/datasets/language/greek"},{"name":"Swahili","url":"/datasets/language/swahili"}],"variants":["MaRVL","IGLUE","XVNLI","xGQA","xFlickr&CO","WIT (IGLUE)"],"data_loaders":[],"num_papers_in_archive":31,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}