{"url":"/dataset/walt","name":"WALT","full_name":"Watch and Learn TimeLapse Images","description_markdown":"We introduce a new dataset, Watch and Learn Time-lapse (WALT), consisting of multiple (4K and 1080p) cameras capturing urban environments over a year.","description_withheld":null,"homepage":"https://www.cs.cmu.edu/~walt/","introduced_date":"2022-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/walt-watch-and-learn-2d-amodal-representation","title":"WALT: Watch and Learn 2D Amodal Representation From Time-Lapse Imagery","first_author":"N. Dinesh Reddy","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Time series","url":"/datasets/modality/time-series"},{"name":"Tracking","url":"/datasets/modality/tracking"}],"tasks":[{"name":"3D Anomaly Detection","url":"/task/3d-anomaly-detection","datasets_with_task":"/datasets/task/3d-anomaly-detection"},{"name":"Amodal Instance Segmentation","url":"/task/amodal-instance-segmentation","datasets_with_task":"/datasets/task/amodal-instance-segmentation"}],"languages":[],"variants":["WALT"],"data_loaders":[{"repo":"https://github.com/dineshreddy91/WALT","url":"https://www.cs.cmu.edu/~walt/license.html","frameworks":["pytorch"]}],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/amodal-instance-segmentation-on-walt","task":"Amodal Instance Segmentation","dataset_variant":"WALT","rows":2,"metrics":["AP"],"first_row_in_archive_order":{"model":"WALTNET","paper":"/paper/walt-watch-and-learn-2d-amodal-representation","metrics":{"AP":"75.3"},"code_links":[{"title":"dineshreddy91/WALT","url":"https://github.com/dineshreddy91/WALT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/walt-watch-and-learn-2d-amodal-representation","title":"WALT: Watch and Learn 2D Amodal Representation From Time-Lapse Imagery","date":"2022-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-occlusion-aware-instance-segmentation","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","date":"2021-03-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":7,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":12,"samples_ran":7,"samples_unverified":5,"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."}