{"url":"/dataset/didi","name":"DiDi","full_name":"Distractor Distilled Dataset","description_markdown":"DiDi is a distractor-distilled tracking dataset created to address the limitation of low distractor presence in current visual object tracking benchmarks. To enhance the evaluation and analysis of tracking performance amidst distractors, we have semi-automatically distilled several existing benchmarks into the DiDi dataset. The dataset is available for download at this URL: https://go.vicos.si/didi","description_withheld":null,"homepage":"https://github.com/jovanavidenovic/DAM4SAM","introduced_date":"2024-11-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-distractor-aware-memory-for-visual-object","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","first_author":"Jovana Videnovic","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Visual Object Tracking","url":"/task/visual-object-tracking","datasets_with_task":"/datasets/task/visual-object-tracking"}],"languages":[],"variants":["DiDi"],"data_loaders":[],"num_papers_in_archive":10,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-object-tracking-on-didi","task":"Visual Object Tracking","dataset_variant":"DiDi","rows":11,"metrics":["Tracking quality"],"first_row_in_archive_order":{"model":"DAM4SAM","paper":"/paper/a-distractor-aware-memory-for-visual-object","metrics":{"Tracking quality":"0.694"},"code_links":[{"title":"jovanavidenovic/dam4sam","url":"https://github.com/jovanavidenovic/dam4sam"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-distractor-aware-memory-for-visual-object","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","date":"2024-11-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":3,"samples_unverified":8,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/samurai-adapting-segment-anything-model-for-1","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","date":"2024-11-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sam2long-enhancing-sam-2-for-long-video","title":"SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","date":"2024-10-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":10,"samples_ran":5,"samples_unverified":5,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":49,"samples_ran":37,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/autoregressive-queries-for-adaptive-tracking","title":"Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers","date":"2024-03-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/odtrack-online-dense-temporal-token-learning","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","date":"2024-01-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/putting-the-object-back-into-video-object","title":"Putting the Object Back into Video Object Segmentation","date":"2023-10-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-target-candidate-association-to-keep","title":"Learning Target Candidate Association to Keep Track of What Not to Track","date":"2021-03-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/2103-15436","title":"Transformer Tracking","date":"2021-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/aot-appearance-optimal-transport-based","title":"AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection","date":"2020-11-05","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":7,"samples_harvested":80,"samples_ran":51,"samples_unverified":29,"pointer_only_for_licence":24,"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."}