{"url":"/dataset/twitter100k","name":"Twitter100k","full_name":null,"description_markdown":"Twitter100k is a large-scale dataset for weakly supervised cross-media retrieval.\r\n\r\nSource: [Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval](/paper/twitter100k-a-real-world-dataset-for-weakly)\r\nImage Source: [https://arxiv.org/pdf/1703.06618v1.pdf](https://arxiv.org/pdf/1703.06618v1.pdf)","description_withheld":null,"homepage":"https://github.com/huyt16/Twitter100k","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/twitter100k-a-real-world-dataset-for-weakly","title":"Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval","first_author":"Yuting Hu","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Cross-Modal Retrieval","url":"/task/cross-modal-retrieval","datasets_with_task":"/datasets/task/cross-modal-retrieval"},{"name":"Quantization","url":"/task/quantization","datasets_with_task":"/datasets/task/quantization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Twitter100k"],"data_loaders":[{"repo":"https://github.com/huyt16/Twitter100k","url":"https://github.com/huyt16/Twitter100k","frameworks":[]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}