{"url":"/dataset/flickr-8k","name":"Flickr-8k","full_name":null,"description_markdown":"Contains 8k flickr Images with captions. Visit [this](http://hockenmaier.cs.illinois.edu/8k-pictures.html) page to explore the data. \r\n\r\nCite this paper if you find it useful in your research: [Framing image description as a ranking task: data, models and evaluation metrics](http://hockenmaier.cs.illinois.edu/Framing_Image_Description/KCCA.html)","description_withheld":null,"homepage":"http://hockenmaier.cs.illinois.edu/8k-pictures.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Creative Commons License 3.0","url":"https://creativecommons.org/licenses/by/3.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Text-to-Image Generation","url":"/task/text-to-image-generation","datasets_with_task":"/datasets/task/text-to-image-generation"},{"name":"Cross-Modal Retrieval","url":"/task/cross-modal-retrieval","datasets_with_task":"/datasets/task/cross-modal-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Flickr-8k"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.Flickr8k.html","frameworks":["pytorch"]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-modal-retrieval-on-flickr-8k","task":"Cross-Modal Retrieval","dataset_variant":"Flickr-8k","rows":1,"metrics":["Image-to-text R@1","Text-to-image R@1"],"first_row_in_archive_order":{"model":"NAPReg","paper":"/paper/napreg-nouns-as-proxies-regularization-for","metrics":{"Image-to-text R@1":"56.2","Text-to-image R@1":"39.2"},"code_links":[{"title":"bhavinjawade/NAPReq","url":"https://github.com/bhavinjawade/NAPReq"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-to-image-generation-on-flickr-8k","task":"Text-to-Image Generation","dataset_variant":"Flickr-8k","rows":1,"metrics":["LPIPS"],"first_row_in_archive_order":{"model":"SSC+SKD","paper":"/paper/language-oriented-communication-with-semantic","metrics":{"LPIPS":"0.697"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/language-oriented-communication-with-semantic","title":"Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image Generation","date":"2023-09-20","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/napreg-nouns-as-proxies-regularization-for","title":"NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings","date":"2023-01-07","rows_on_this_dataset":1,"code_links":1,"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."}