{"url":"/dataset/tacos-multi-level-corpus","name":"TACoS Multi-Level Corpus","full_name":null,"description_markdown":"Augments the video-description dataset TACoS with short and single sentence descriptions.\r\n\r\nSource: [Coherent Multi-Sentence Video Description with Variable Level of Detail](/paper/coherent-multi-sentence-video-description)","description_withheld":null,"homepage":"http://www.mpi-inf.mpg.de/tacos","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/coherent-multi-sentence-video-description","title":"Coherent Multi-Sentence Video Description with Variable Level of Detail","first_author":"Anna Senina","url":null},"license":null,"modalities":[],"tasks":[{"name":"Activity Recognition","url":"/task/activity-recognition","datasets_with_task":"/datasets/task/activity-recognition"},{"name":"Natural Language Moment Retrieval","url":"/task/natural-language-moment-retrieval","datasets_with_task":"/datasets/task/natural-language-moment-retrieval"},{"name":"Video Description","url":"/task/video-description","datasets_with_task":"/datasets/task/video-description"}],"languages":[],"variants":["TACoS","TACoS Multi-Level Corpus"],"data_loaders":[],"num_papers_in_archive":45,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/natural-language-moment-retrieval-on-tacos","task":"Natural Language Moment Retrieval","dataset_variant":"TACoS","rows":13,"metrics":["R@1,IoU=0.3","R@1,IoU=0.5","R@1,IoU=0.7","R@5,IoU=0.1","R@5,IoU=0.3","R@5,IoU=0.5","mIoU"],"first_row_in_archive_order":{"model":"SG-DETR (w/ PT)","paper":"/paper/saliency-guided-detr-for-moment-retrieval-and","metrics":{"R@1,IoU=0.3":"58.10","R@1,IoU=0.5":"46.40","R@1,IoU=0.7":"33.90","mIoU":"42.40"},"code_links":[{"title":"ai-forever/sg-detr","url":"https://github.com/ai-forever/sg-detr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/decafnet-delegate-and-conquer-for-efficient","title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","date":"2025-05-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ld-detr-loop-decoder-detection-transformer","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","date":"2025-01-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/flashvtg-feature-layering-and-adaptive-score","title":"FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding","date":"2024-12-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":2,"samples_unverified":11,"pointer_only_for_licence":13,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/saliency-guided-detr-for-moment-retrieval-and","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","date":"2024-10-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bam-detr-boundary-aligned-moment-detection","title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","date":"2023-11-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":8,"samples_unverified":3,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bridging-the-gap-a-unified-video","title":"Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection","date":"2023-11-28","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":9,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/correlation-guided-query-dependency","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","date":"2023-11-15","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":2,"samples_unverified":9,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/univtg-towards-unified-video-language","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","date":"2023-07-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":10,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-grounded-vision-language","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","date":"2023-03-11","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":1,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vlg-net-video-language-graph-matching-network","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","date":"2020-11-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+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."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":8,"samples_harvested":87,"samples_ran":38,"samples_unverified":49,"pointer_only_for_licence":35,"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."}