{"url":"/task/temporal-sentence-grounding","name":"Temporal Sentence Grounding","slug":"temporal-sentence-grounding","description_markdown":"Temporal sentence grounding (TSG) aims to locate a specific moment from an untrimmed video with a given natural language query. For this task, different levels of supervision are used. 1) Weak supervision: video-level action category set; 2) Semi-weak supervision: video-level action category set, and action annotations at several timestamps; 3) Full supervision: Action category and action interval annotations of all actions in untrimmed videos.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":43,"papers_with_code":16,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/temporal-sentence-grounding-on-charades-sta","slug":"temporal-sentence-grounding-on-charades-sta","dataset":"Charades-STA","dataset_url":"/dataset/charades-sta","rows_in_archive":13,"metrics":["R1@0.7","R1@0.5","R5@0.7","R5@0.5"],"first_row_in_archive_order":{"model":"DeCafNet","paper_title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","paper_url":"/paper/decafnet-delegate-and-conquer-for-efficient","paper_date":"2025-05-22","arxiv_id":"2505.16376","code_links":[{"title":"zijialewislu/cvpr2025-decafnet","url":"https://github.com/zijialewislu/cvpr2025-decafnet"}],"syntology":null}},{"leaderboard":"/sota/temporal-sentence-grounding-on-ego4d-goalstep","slug":"temporal-sentence-grounding-on-ego4d-goalstep","dataset":"Ego4D-Goalstep","dataset_url":null,"rows_in_archive":3,"metrics":["R@1,IoU=0.3","R@1,IoU=0.5","R@5,IoU=0.3","R@5,IoU=0.5"],"first_row_in_archive_order":{"model":"DeCafNet-100%","paper_title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","paper_url":"/paper/decafnet-delegate-and-conquer-for-efficient","paper_date":"2025-05-22","arxiv_id":"2505.16376","code_links":[{"title":"zijialewislu/cvpr2025-decafnet","url":"https://github.com/zijialewislu/cvpr2025-decafnet"}],"syntology":null}}],"datasets":[{"url":"/dataset/charades-sta","name":"Charades-STA","full_name":"","num_papers_in_archive":236}],"subtasks":[],"parent_tasks":[{"url":"/task/video-understanding","name":"Video Understanding"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":16,"of":16,"tagged_in_all":43,"items":[{"url":"/paper/negative-sample-matters-a-renaissance-of","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","date":"2021-09-10","arxiv_id":"2109.04872","repositories_listed":2,"syntology":null},{"url":"/paper/decafnet-delegate-and-conquer-for-efficient","title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","date":"2025-05-22","arxiv_id":"2505.16376","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-videollm-sharpening-fine-grained","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","date":"2024-10-04","arxiv_id":"2410.03290","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/transformer-with-controlled-attention-for","title":"Transformer with Controlled Attention for Synchronous Motion Captioning","date":"2024-09-13","arxiv_id":"2409.09177","repositories_listed":1,"syntology":null},{"url":"/paper/diversifying-query-region-guided-transformer","title":"Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding","date":"2024-05-31","arxiv_id":"2406.00143","repositories_listed":1,"syntology":null},{"url":"/paper/bias-conflict-sample-synthesis-and","title":"Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video","date":"2024-01-15","arxiv_id":"2401.07567","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}},{"url":"/paper/gaussian-mixture-proposals-with-pull-push","title":"Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding","date":"2023-12-27","arxiv_id":"2312.16388","repositories_listed":1,"syntology":null},{"url":"/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","arxiv_id":"2312.00083","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":11}},{"url":"/paper/learning-temporal-sentence-grounding-from","title":"Learning Temporal Sentence Grounding From Narrated EgoVideos","date":"2023-10-26","arxiv_id":"2310.17395","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-sentence-grounding-in-streaming","title":"Temporal Sentence Grounding in Streaming Videos","date":"2023-08-14","arxiv_id":"2308.07102","repositories_listed":1,"syntology":null},{"url":"/paper/d3g-exploring-gaussian-prior-for-temporal","title":"D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation","date":"2023-08-08","arxiv_id":"2308.04197","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_unverified":4,"n_pointer_only":17}},{"url":"/paper/efficient-temporal-sentence-grounding-in","title":"Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation","date":"2023-08-07","arxiv_id":"2308.03725","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-temporal-sentence-grounding","title":"Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/uncovering-hidden-challenges-in-query-based","title":"Uncovering Hidden Challenges in Query-Based Video Moment Retrieval","date":"2020-09-01","arxiv_id":"2009.00325","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/span-based-localizing-network-for-natural","title":"Span-based Localizing Network for Natural Language Video Localization","date":"2020-04-29","arxiv_id":"2004.13931","repositories_listed":1,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/semantic-conditioned-dynamic-modulation-for","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","date":"2019-10-31","arxiv_id":"1910.14303","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}