{"url":"/dataset/icm","name":"ICM","full_name":"Image-Caption Matching Dataset","description_markdown":"ICM is curated for the image-text matching task. Each image has a corresponding caption text, which describes the image in detail. We first use CTR to select the most relevant pairs. Then, human annotators manually perform a 2nd round manual correction, obtaining 400,000 image-text pairs, including 200,000 positive cases and 200,000 negative cases. We keep the ratio of positive and negative pairs consistent in each of the train/val/test sets.","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":["ICM"],"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."}