{"url":"/dataset/coco-cn","name":"COCO-CN","full_name":null,"description_markdown":"COCO-CN is a bilingual image description dataset enriching MS-COCO with manually written Chinese sentences and tags. The new dataset can be used for multiple tasks including image tagging, captioning and retrieval, all in a cross-lingual setting.\r\n\r\nSource: [COCO-CN](https://github.com/li-xirong/coco-cn)","description_withheld":null,"homepage":"https://github.com/li-xirong/coco-cn","introduced_date":"2018-05-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/coco-cn-for-cross-lingual-image-tagging","title":"COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval","first_author":"Xirong Li","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Zero-shot Image Retrieval","url":"/task/zero-shot-image-retrieval","datasets_with_task":"/datasets/task/zero-shot-image-retrieval"},{"name":"Zero-shot Text-to-Image Retrieval","url":"/task/zero-shot-text-to-image-retrieval","datasets_with_task":"/datasets/task/zero-shot-text-to-image-retrieval"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["COCO-CN"],"data_loaders":[{"repo":"https://github.com/li-xirong/coco-cn","url":"https://github.com/li-xirong/coco-cn","frameworks":[]}],"num_papers_in_archive":21,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-retrieval-on-coco-cn","task":"Image Retrieval","dataset_variant":"COCO-CN","rows":9,"metrics":["R@1","R@10","R@5"],"first_row_in_archive_order":{"model":"CN-CLIP (ViT-H/14)","paper":"/paper/chinese-clip-contrastive-vision-language","metrics":{"R@1":"81.5","R@10":"99.1","R@5":"96.9"},"code_links":[{"title":"ofa-sys/chinese-clip","url":"https://github.com/ofa-sys/chinese-clip"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/chinese-clip-contrastive-vision-language","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","date":"2022-11-02","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/zero-and-r2d2-a-large-scale-chinese-cross","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","date":"2022-05-08","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":9,"samples_ran":8,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/wukong-100-million-large-scale-chinese-cross","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","date":"2022-02-14","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":3,"samples_harvested":18,"samples_ran":14,"samples_unverified":4,"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."}