{"url":"/dataset/arvsu","name":"ARVSU","full_name":"Addressee Recognition in Visual Scenes with Utterances","description_markdown":"ARVSU contains a vast body of image variations in visual scenes with an annotated utterance and a corresponding addressee for each scenario.\r\n\r\nSource: [Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances](https://arxiv.org/pdf/1809.04288)","description_withheld":null,"homepage":"https://arxiv.org/pdf/1809.04288.pdf","introduced_date":"2018-09-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-learning-based-multi-modal-addressee","title":"Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances","first_author":"Thao Minh Le","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[],"languages":[],"variants":["ARVSU"],"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."}