{"url":"/dataset/flickrstyle10k","name":"FlickrStyle10K","full_name":null,"description_markdown":"FlickrStyle10K is collected and built on Flickr30K image caption dataset. The original FlickrStyle10K dataset has 10,000 pairs of images and stylized captions including humorous and romantic styles. However, only 7,000 pairs from the official training set are now publicly accessible. The dataset can be downloaded via https://zhegan27.github.io/Papers/FlickrStyle_v0.9.zip","description_withheld":null,"homepage":"https://zhegan27.github.io/Papers/FlickrStyle_v0.9.zip","introduced_date":"2017-07-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/stylenet-generating-attractive-visual","title":"StyleNet: Generating Attractive Visual Captions With Styles","first_author":"Chuang Gan","url":null},"license":{"name":"Unknown","url":"https://paperswithcode.com"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Semi Supervised Learning for Image Captioning","url":"/task/semi-supervised-learning-for-image-captioning","datasets_with_task":"/datasets/task/semi-supervised-learning-for-image-captioning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["FlickrStyle10K"],"data_loaders":[],"num_papers_in_archive":24,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-captioning-on-flickrstyle10k","task":"Image Captioning","dataset_variant":"FlickrStyle10K","rows":2,"metrics":["BLEU-1 (Romantic)"],"first_row_in_archive_order":{"model":"CapDec","paper":"/paper/text-only-training-for-image-captioning-using","metrics":{"BLEU-1 (Romantic)":"29.4"},"code_links":[{"title":"davidhuji/capdec","url":"https://github.com/davidhuji/capdec"},{"title":"zelaki/wsac","url":"https://github.com/zelaki/wsac"},{"title":"avitej-iyer/CapDec-Recreation","url":"https://github.com/avitej-iyer/CapDec-Recreation"},{"title":"uriberger/re_cap","url":"https://github.com/uriberger/re_cap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-learning-for-image-captioning-3","task":"Semi Supervised Learning for Image Captioning","dataset_variant":"FlickrStyle10K","rows":1,"metrics":["CIDEr"],"first_row_in_archive_order":{"model":"CapDec","paper":"/paper/text-only-training-for-image-captioning-using","metrics":{"CIDEr":"30.0"},"code_links":[{"title":"davidhuji/capdec","url":"https://github.com/davidhuji/capdec"},{"title":"zelaki/wsac","url":"https://github.com/zelaki/wsac"},{"title":"avitej-iyer/CapDec-Recreation","url":"https://github.com/avitej-iyer/CapDec-Recreation"},{"title":"uriberger/re_cap","url":"https://github.com/uriberger/re_cap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/memcap-memorizing-style-knowledge-for-image","title":"MemCap: Memorizing Style Knowledge for Image Captioning","date":"2020-04-03","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":1,"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."}