{"url":"/dataset/slim","name":"Slim","full_name":"Slim","description_markdown":"This dataset consists of virtual scenes rendered in MuJoCo with multiple views each presented in multiple modalities: image, and synthetic or natural language descriptions. Each scene consists of two or three objects placed on a square walled room, and for each of the 10 camera viewpoint the authors rendered a 3D view of the scene as seen from that viewpoint as well as a synthetically generated description of the scene.\r\n\r\nSource: [GitHub](https://github.com/deepmind/slim-dataset)","description_withheld":null,"homepage":"https://github.com/deepmind/slim-dataset","introduced_date":"2018-07-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/encoding-spatial-relations-from-natural","title":"Encoding Spatial Relations from Natural Language","first_author":"Tiago Ramalho","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["Slim"],"data_loaders":[{"repo":"https://github.com/deepmind/slim-dataset","url":"https://github.com/deepmind/slim-dataset","frameworks":["tf"]}],"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."}