{"url":"/dataset/ivm-mix-1m","name":"IVM-Mix-1M","full_name":null,"description_markdown":"IVM-Mix-1M provide over 1M image-instruction pairs with corresponding instruction-relevant mask labels. Our IVM-Mix-1M dataset consists of three part: HumanLabelData, RobotMachineData and VQAMachineData. For the HumanLabelData and RobotMachineData, we provide well-orgnized images, mask label and language instructions. For the VQAMachineData, we only provide mask label and language instructions, please refer to https://huggingface.co/datasets/2toINF/IVM-Mix-1M and download the images from constituting datasets.","description_withheld":null,"homepage":"https://huggingface.co/datasets/2toINF/IVM-Mix-1M","introduced_date":"2024-05-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/instruction-guided-visual-masking","title":"Instruction-Guided Visual Masking","first_author":"Jinliang Zheng","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["IVM-Mix-1M"],"data_loaders":[],"num_papers_in_archive":1,"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."}