{"url":"/dataset/icr","name":"ICR","full_name":"Image-Caption Retrieval Dataset","description_markdown":"In this dataset, we collect 200,000 image-text pairs. Each image has a corresponding caption text, which describes the image in detail. It contains two subtasks: \r\nimage-to-text retrieval and text-to-image retrieval tasks.","description_withheld":null,"homepage":"https://zero.so.com/","introduced_date":"2022-05-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/zero-and-r2d2-a-large-scale-chinese-cross","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","first_author":"Chunyu Xie","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["ICR"],"data_loaders":[],"num_papers_in_archive":1,"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."}