{"url":"/dataset/hc-stvg1","name":"HC-STVG1","full_name":"Human-centric Spatio-Temporal Video Grounding","description_markdown":"The newly proposed HC-STVG task aims to localize the target person spatio-temporally in an untrimmed video. For this task, we collect a new benchmark dataset, which has spatio temporal annotations related to the target persons in complex multi-person scenes, together with full interaction and rich action information.","description_withheld":null,"homepage":"https://github.com/tzhhhh123/HC-STVG","introduced_date":"2020-11-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/human-centric-spatio-temporal-video-grounding","title":"Human-centric Spatio-Temporal Video Grounding With Visual Transformers","first_author":"Zongheng Tang","url":null},"license":null,"modalities":[],"tasks":[{"name":"Spatio-Temporal Video Grounding","url":"/task/spatio-temporal-video-grounding","datasets_with_task":"/datasets/task/spatio-temporal-video-grounding"}],"languages":[],"variants":["HC-STVG1"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/spatio-temporal-video-grounding-on-hc-stvg1","task":"Spatio-Temporal Video Grounding","dataset_variant":"HC-STVG1","rows":3,"metrics":["m_vIoU","vIoU@0.3","vIoU@0.5"],"first_row_in_archive_order":{"model":"TA-STVG","paper":"/paper/knowing-your-target-target-aware-transformer","metrics":{"m_vIoU":"39.1","vIoU@0.3":"63.1","vIoU@0.5":"36.8"},"code_links":[{"title":"HengLan/TA-STVG","url":"https://github.com/HengLan/TA-STVG"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/knowing-your-target-target-aware-transformer","title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","date":"2025-02-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/context-guided-spatio-temporal-video","title":"Context-Guided Spatio-Temporal Video Grounding","date":"2024-01-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":34,"samples_ran":21,"samples_unverified":13,"pointer_only_for_licence":34,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tubedetr-spatio-temporal-video-grounding-with","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","date":"2022-03-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"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":2,"samples_harvested":37,"samples_ran":24,"samples_unverified":13,"pointer_only_for_licence":34,"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."}