{"url":"/dataset/advance","name":"ADVANCE","full_name":"AuDio Visual Aerial sceNe reCognition datasEt","description_markdown":"The AuDio Visual Aerial sceNe reCognition datasEt (ADVANCE) is a brand-new multimodal learning dataset, which aims to explore the contribution of both audio and conventional visual messages to scene recognition. This dataset in summary contains 5075 pairs of geotagged aerial images and sounds, classified into 13 scene classes, i.e., airport, sports land, beach, bridge, farmland, forest, grassland, harbor, lake, orchard, residential area, shrub land, and train station.\r\n\r\nSource: [](https://akchen.github.io/ADVANCE-DATASET/)","description_withheld":null,"homepage":"https://akchen.github.io/ADVANCE-DATASET/","introduced_date":"2020-05-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/cross-task-transfer-for-multimodal-aerial","title":"Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition","first_author":"Di Hu","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Scene Recognition","url":"/task/scene-recognition","datasets_with_task":"/datasets/task/scene-recognition"}],"languages":[],"variants":["ADVANCE"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/blanchon/ADVANCE","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":6,"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."}