{"url":"/task/generalized-referring-expression","name":"Generalized Referring Expression Comprehension","slug":"generalized-referring-expression","description_markdown":"Generalized Referring Expression Comprehension (GREC) allows expressions indicating any number of target objects. GREC takes an image and a referring expression as input, and requires bounding box(es) prediction of the target object(s).","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":7,"papers_with_code":6,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/generalized-referring-expression","slug":"generalized-referring-expression","dataset":"gRefCOCO","dataset_url":"/dataset/grefcoco","rows_in_archive":5,"metrics":["Precision@(F1=1, IoU≥0.5)","N-acc."],"first_row_in_archive_order":{"model":"SimVG-DB","paper_title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","paper_url":"/paper/simvg-a-simple-framework-for-visual-grounding","paper_date":"2024-09-26","arxiv_id":"2409.17531","code_links":[{"title":"dmmm1997/simvg","url":"https://github.com/dmmm1997/simvg"}],"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/grefcoco","name":"gRefCOCO","full_name":"","num_papers_in_archive":43}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":6,"of":6,"tagged_in_all":7,"items":[{"url":"/paper/mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","repositories_listed":5,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/multi-task-collaborative-network-for-joint","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","date":"2020-03-19","arxiv_id":"2003.08813","repositories_listed":2,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/simvg-a-simple-framework-for-visual-grounding","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","date":"2024-09-26","arxiv_id":"2409.17531","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/grec-generalized-referring-expression","title":"GREC: Generalized Referring Expression Comprehension","date":"2023-08-30","arxiv_id":"2308.16182","repositories_listed":1,"syntology":null},{"url":"/paper/universal-instance-perception-as-object","title":"Universal Instance Perception as Object Discovery and Retrieval","date":"2023-03-12","arxiv_id":"2303.06674","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/vision-language-transformer-and-query","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2021-08-12","arxiv_id":"2108.05565","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}