{"url":"/dataset/cc152k","name":"CC152K","full_name":"Conceptual Captions 152K","description_markdown":"CC152K is a subset of Conceptual Captions. It contains 150,000 randomly selected samples from the training split for training, 1,000 samples from the validation split for validation, and 1,000 samples from the validation split for testing.","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/cross-modal-retrieval-with-noisy","title":"Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining","first_author":"Xinran Ma","url":null},"license":null,"modalities":[],"tasks":[{"name":"Cross-modal retrieval with noisy correspondence","url":"/task/cross-modal-retrieval-with-noisy","datasets_with_task":"/datasets/task/cross-modal-retrieval-with-noisy"}],"languages":[],"variants":["CC152K"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-1","task":"Cross-modal retrieval with noisy correspondence","dataset_variant":"CC152K","rows":15,"metrics":["R-Sum","Image-to-text R@1","Image-to-text R@5","Image-to-text R@10","Text-to-image R@1","Text-to-image R@5","Text-to-image R@10"],"first_row_in_archive_order":{"model":"ReCon","paper":"/paper/recon-enhancing-true-correspondence-1","metrics":{"Image-to-text R@1":"43.1","Image-to-text R@10":"78.1","Image-to-text R@5":"68.7","R-Sum":"380.5","Text-to-image R@1":"44.9","Text-to-image R@10":"77.4","Text-to-image R@5":"68.3"},"code_links":[{"title":"qxzha/ReCon","url":"https://github.com/qxzha/ReCon"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/recon-enhancing-true-correspondence-1","title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","date":"2025-02-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ugncl-uncertainty-guided-noisy-correspondence","title":"UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching","date":"2024-07-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mitigating-noisy-correspondence-by","title":"Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning","date":"2024-05-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-with-noisy-correspondence","title":"Learning with Noisy Correspondence","date":"2024-04-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-modal-retrieval-with-noisy","title":"Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining","date":"2024-03-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nac-mitigating-noisy-correspondence-in-cross","title":"NAC: Mitigating Noisy Correspondence in Cross-Modal Matching Via Neighbor Auxiliary Corrector","date":"2024-03-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/repair-rank-correlation-and-noisy-pair-half","title":"REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence","date":"2024-03-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-to-rematch-mismatched-pairs-for","title":"Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval","date":"2024-03-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":8,"samples_unverified":2,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/noisy-correspondence-learning-with-self","title":"Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation","date":"2023-12-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-modal-active-complementary-learning-1","title":"Cross-modal Active Complementary Learning with Self-refining Correspondence","date":"2023-10-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":28,"samples_ran":23,"samples_unverified":5,"pointer_only_for_licence":28,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/noisy-correspondence-learning-with-meta","title":"Noisy Correspondence Learning with Meta Similarity Correction","date":"2023-04-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bicro-noisy-correspondence-rectification-for","title":"BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency","date":"2023-03-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":9,"samples_unverified":2,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cross-modal-retrieval-with-partially","title":"Cross-Modal Retrieval with Partially Mismatched Pairs","date":"2023-02-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-evidential-learning-with-noisy","title":"Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval","date":"2022-10-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-with-noisy-correspondence-for-cross","title":"Learning with Noisy Correspondence for Cross-modal Matching","date":"2021-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":6,"samples_harvested":62,"samples_ran":49,"samples_unverified":13,"pointer_only_for_licence":55,"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."}