{"url":"/sota/image-retrieval-on-coco-cn","task":{"name":"Image Retrieval","url":"/task/image-retrieval","note":null},"dataset":{"name":"COCO-CN","url":"/dataset/coco-cn"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Image Retrieval** is a fundamental and long-standing computer vision task that involves finding images similar to a given query from a large database. It is often considered a form of fine-grained, instance-level classification. The task is integral to image recognition alongside [classification](/task/image-classification) and [cross-modal retrieval](/task/cross-modal-retrieva). By leveraging visual similarity and other criteria, image retrieval enables users to efficiently discover relevant images, making it a crucial tool in applications such as search and recommendation.\r\n\r\n<span class=\"description-source\">[Extending CLIP for Category-to-image Retrieval in E-commerce](https://arxiv.org/abs/2112.11294)</span>\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [DELF](https://github.com/tensorflow/models/tree/master/research/delf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["R@1","R@10","R@5"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"R@1":null,"R@10":null,"R@5":null}},"counts":{"rows":9,"rows_with_code":9,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CN-CLIP (ViT-H/14)","metrics":{"R@1":"81.5","R@10":"99.1","R@5":"96.9"},"uses_additional_data":false,"paper_date":"2022-11-02","paper":"/paper/chinese-clip-contrastive-vision-language","paper_url":"https://arxiv.org/abs/2211.01335v3","paper_title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","code":"https://github.com/ofa-sys/chinese-clip","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"CN-CLIP (ViT-L/14@336px)","metrics":{"R@1":"80.1","R@10":"99.2","R@5":"96.7"},"uses_additional_data":false,"paper_date":"2022-11-02","paper":"/paper/chinese-clip-contrastive-vision-language","paper_url":"https://arxiv.org/abs/2211.01335v3","paper_title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","code":"https://github.com/ofa-sys/chinese-clip","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"R2D2 (ViT-L/14)","metrics":{"R@1":"79.1","R@10":"98.9","R@5":"96.5"},"uses_additional_data":false,"paper_date":"2022-05-08","paper":"/paper/zero-and-r2d2-a-large-scale-chinese-cross","paper_url":"https://arxiv.org/abs/2205.03860v6","paper_title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","code":"https://github.com/yuxie11/R2D2","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"CN-CLIP (ViT-L/14)","metrics":{"R@1":"78.9","R@10":"99.0","R@5":"96.3"},"uses_additional_data":false,"paper_date":"2022-11-02","paper":"/paper/chinese-clip-contrastive-vision-language","paper_url":"https://arxiv.org/abs/2211.01335v3","paper_title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","code":"https://github.com/ofa-sys/chinese-clip","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"CN-CLIP (ViT-B/16)","metrics":{"R@1":"77.0","R@10":"99.0","R@5":"97.1"},"uses_additional_data":false,"paper_date":"2022-11-02","paper":"/paper/chinese-clip-contrastive-vision-language","paper_url":"https://arxiv.org/abs/2211.01335v3","paper_title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","code":"https://github.com/ofa-sys/chinese-clip","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"R2D2 (ViT-B)","metrics":{"R@1":"75.1","R@10":"98.1","R@5":"94.2"},"uses_additional_data":false,"paper_date":"2022-05-08","paper":"/paper/zero-and-r2d2-a-large-scale-chinese-cross","paper_url":"https://arxiv.org/abs/2205.03860v6","paper_title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","code":"https://github.com/yuxie11/R2D2","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"Wukong (ViT-L/14)","metrics":{"R@1":"74.0","R@10":"98.1","R@5":"94.4"},"uses_additional_data":false,"paper_date":"2022-02-14","paper":"/paper/wukong-100-million-large-scale-chinese-cross","paper_url":"https://arxiv.org/abs/2202.06767v4","paper_title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","code":"https://github.com/0jason000/wukong","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"Wukong (ViT-B/32)","metrics":{"R@1":"67.0","R@10":"96.7","R@5":"91.4"},"uses_additional_data":false,"paper_date":"2022-02-14","paper":"/paper/wukong-100-million-large-scale-chinese-cross","paper_url":"https://arxiv.org/abs/2202.06767v4","paper_title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","code":"https://github.com/0jason000/wukong","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"CN-CLIP (RN50)","metrics":{"R@1":"66.8","R@10":"97.0","R@5":"91.1"},"uses_additional_data":false,"paper_date":"2022-11-02","paper":"/paper/chinese-clip-contrastive-vision-language","paper_url":"https://arxiv.org/abs/2211.01335v3","paper_title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","code":"https://github.com/ofa-sys/chinese-clip","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":9,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":14,"n_samples":18,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":20,"n_unverified":37,"n_samples":57,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}