{"url":"/dataset/cxc","name":"CxC","full_name":"Crisscrossed Captions","description_markdown":"Crisscrossed Captions (CxC) contains 247,315 human-labeled annotations including positive and negative associations between image pairs, caption pairs and image-caption pairs.\r\n\r\nImage source: [Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO](https://arxiv.org/pdf/2004.15020.pdf)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/Crisscrossed-Captions","introduced_date":"2020-04-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/crisscrossed-captions-extended-intramodal-and","title":"Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO","first_author":"Zarana Parekh","url":null},"license":{"name":"Custom","url":"https://github.com/google-research-datasets/Crisscrossed-Captions/blob/master/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","datasets_with_task":"/datasets/task/semantic-textual-similarity"},{"name":"Semantic Image Similarity","url":"/task/semantic-image-similarity","datasets_with_task":"/datasets/task/semantic-image-similarity"},{"name":"Semantic Image-Text Similarity","url":"/task/semantic-image-text-similarity","datasets_with_task":"/datasets/task/semantic-image-text-similarity"}],"languages":[],"variants":["CxC"],"data_loaders":[{"repo":"https://github.com/google-research-datasets/Crisscrossed-Captions","url":"https://github.com/google-research-datasets/Crisscrossed-Captions","frameworks":[]}],"num_papers_in_archive":22,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-textual-similarity-on-cxc","task":"Semantic Textual Similarity","dataset_variant":"CxC","rows":4,"metrics":["avg ± std"],"first_row_in_archive_order":{"model":"PromCSE-RoBERTa-large (0.355B)","paper":"/paper/deep-continuous-prompt-for-contrastive-1","metrics":{"avg ± std":"74.8± 1.0"},"code_links":[{"title":"yjiangcm/promcse","url":"https://github.com/yjiangcm/promcse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/deep-continuous-prompt-for-contrastive-1","title":"Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning","date":"2022-03-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mural-multimodal-multitask-retrieval-across","title":"MURAL: Multimodal, Multitask Retrieval Across Languages","date":"2021-09-10","rows_on_this_dataset":3,"code_links":0,"syntology":null}],"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."}