{"url":"/dataset/open-images-v4","name":"Open Images V4","full_name":null,"description_markdown":"Open Images V4 offers large scale across several dimensions: 30.1M image-level labels for 19.8k concepts, 15.4M bounding boxes for 600 object classes, and 375k visual relationship annotations involving 57 classes. For object detection in particular, 15x more bounding boxes than the next largest datasets (15.4M boxes on 1.9M images) are provided. The images often show complex scenes with several objects (8 annotated objects per image on average). Visual relationships between them are annotated, which support visual relationship detection, an emerging task that requires structured reasoning.\r\n\r\nSource: [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://arxiv.org/pdf/1811.00982)\r\nImage Source: [https://storage.googleapis.com/openimages/web/index.html](https://storage.googleapis.com/openimages/web/index.html)","description_withheld":null,"homepage":"https://storage.googleapis.com/openimages/web/index.html","introduced_date":"2018-11-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-open-images-dataset-v4-unified-image","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","first_author":"Alina Kuznetsova","url":null},"license":{"name":"Custom","url":"https://storage.googleapis.com/openimages/web/download.html"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Multi-label zero-shot learning","url":"/task/multi-label-zero-shot-learning","datasets_with_task":"/datasets/task/multi-label-zero-shot-learning"}],"languages":[],"variants":["Open Images V4"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/open_images_v4","frameworks":["tf","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/open_images_challenge2019_detection","frameworks":["tf","jax"]}],"num_papers_in_archive":37,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-label-zero-shot-learning-on-open-images","task":"Multi-label zero-shot learning","dataset_variant":"Open Images V4","rows":8,"metrics":["MAP"],"first_row_in_archive_order":{"model":"MKT(IN-1K)","paper":"/paper/open-vocabulary-multi-label-classification","metrics":{"MAP":"89.2"},"code_links":[{"title":"sunanhe/mkt","url":"https://github.com/sunanhe/mkt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/open-vocabulary-multi-label-classification","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","date":"2022-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/discriminative-region-based-multi-label-zero","title":"Discriminative Region-based Multi-Label Zero-Shot Learning","date":"2021-08-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":7,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantic-diversity-learning-for-zero-shot","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","date":"2021-05-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-shared-multi-attention-framework-for-multi","title":"A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning","date":"2020-06-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/fast-zero-shot-image-tagging","title":"Fast Zero-Shot Image Tagging","date":"2016-05-31","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/label-embedding-for-image-classification","title":"Label-Embedding for Image Classification","date":"2015-03-30","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/zero-shot-learning-by-convex-combination-of","title":"Zero-Shot Learning by Convex Combination of Semantic Embeddings","date":"2013-12-19","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":17,"samples_ran":10,"samples_unverified":7,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":1,"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."}