{"url":"/dataset/mcic-coco","name":"MCIC-COCO","full_name":null,"description_markdown":"A large-scale machine comprehension dataset (based on the COCO images and captions).\r\n\r\nSource: [Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task](/paper/understanding-image-and-text-simultaneously-a)","description_withheld":null,"homepage":"https://github.com/google/mcic-coco","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/understanding-image-and-text-simultaneously-a","title":"Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task","first_author":"Nan Ding","url":null},"license":null,"modalities":[],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"}],"languages":[],"variants":["MCIC-COCO"],"data_loaders":[{"repo":"https://github.com/google/mcic-coco","url":"https://github.com/google/mcic-coco","frameworks":[]}],"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."}