{"url":"/dataset/phrasecut","name":"PhraseCut","full_name":null,"description_markdown":"**PhraseCut** is a dataset consisting of 77,262 images and 345,486 phrase-region pairs. The dataset is collected on top of the Visual Genome dataset and uses the existing annotations to generate a challenging set of referring phrases for which the corresponding regions are manually annotated.\r\n\r\nSource: [PhraseCut: Language-based Image Segmentation in the Wild](/paper/phrasecut-language-based-image-segmentation-1)\r\nImage Source: [https://people.cs.umass.edu/~chenyun/publication/phrasecut/](https://people.cs.umass.edu/~chenyun/publication/phrasecut/)","description_withheld":null,"homepage":"https://people.cs.umass.edu/~chenyun/publication/phrasecut/","introduced_date":"2020-05-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/phrasecut-language-based-image-segmentation-1","title":"PhraseCut: Language-based Image Segmentation in the Wild","first_author":"Chenyun Wu","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Referring Expression Segmentation","url":"/task/referring-expression-segmentation","datasets_with_task":"/datasets/task/referring-expression-segmentation"}],"languages":[],"variants":["PhraseCut"],"data_loaders":[],"num_papers_in_archive":31,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/referring-expression-segmentation-on","task":"Referring Expression Segmentation","dataset_variant":"PhraseCut","rows":6,"metrics":["Mean IoU","Pr@0.5","Pr@0.7","Pr@0.9"],"first_row_in_archive_order":{"model":"GLIPv2","paper":"/paper/glipv2-unifying-localization-and-vision","metrics":{"Mean IoU":"61.3"},"code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/groundhog-grounding-large-language-models-to","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","date":"2024-02-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/glipv2-unifying-localization-and-vision","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","date":"2022-06-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":6,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/phrasecut-language-based-image-segmentation-1","title":"PhraseCut: Language-based Image Segmentation in the Wild","date":"2020-08-03","rows_on_this_dataset":3,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":13,"samples_ran":8,"samples_unverified":5,"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."}