{"url":"/task/visual-keyword-spotting","name":"Visual Keyword Spotting","slug":"visual-keyword-spotting","description_markdown":"Spot a given query keyword in a silent talking face video","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":5,"papers_with_code":4,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/visual-keyword-spotting-on-lrs2","slug":"visual-keyword-spotting-on-lrs2","dataset":"LRS2","dataset_url":"/dataset/lrs2","rows_in_archive":1,"metrics":["Top-1 Accuracy","Top-5 Accuracy","mAP","mAP IOU@0.5"],"first_row_in_archive_order":{"model":"Transpotter","paper_title":"Visual Keyword Spotting with Attention","paper_url":"/paper/visual-keyword-spotting-with-attention","paper_date":"2021-10-29","arxiv_id":"2110.15957","code_links":[{"title":"prajwalkr/transpotter","url":"https://github.com/prajwalkr/transpotter"}],"syntology":null}},{"leaderboard":"/sota/visual-keyword-spotting-on-lrs3-ted","slug":"visual-keyword-spotting-on-lrs3-ted","dataset":"LRS3-TED","dataset_url":"/dataset/lrs3-ted","rows_in_archive":1,"metrics":["Top-1 Accuracy","Top-5 Accuracy","mAP","mAP IOU@0.5"],"first_row_in_archive_order":{"model":"Transpotter","paper_title":"Visual Keyword Spotting with Attention","paper_url":"/paper/visual-keyword-spotting-with-attention","paper_date":"2021-10-29","arxiv_id":"2110.15957","code_links":[{"title":"prajwalkr/transpotter","url":"https://github.com/prajwalkr/transpotter"}],"syntology":null}},{"leaderboard":"/sota/visual-keyword-spotting-on-lrw","slug":"visual-keyword-spotting-on-lrw","dataset":"LRW","dataset_url":"/dataset/lrw","rows_in_archive":1,"metrics":["Top-1 Accuracy","Top-5 Accuracy","mAP"],"first_row_in_archive_order":{"model":"Transpotter","paper_title":"Visual Keyword Spotting with Attention","paper_url":"/paper/visual-keyword-spotting-with-attention","paper_date":"2021-10-29","arxiv_id":"2110.15957","code_links":[{"title":"prajwalkr/transpotter","url":"https://github.com/prajwalkr/transpotter"}],"syntology":null}}],"datasets":[{"url":"/dataset/lrw","name":"LRW","full_name":"Lip Reading in the Wild","num_papers_in_archive":188},{"url":"/dataset/lrs2","name":"LRS2","full_name":"Lip Reading Sentences 2","num_papers_in_archive":115},{"url":"/dataset/lrs3-ted","name":"LRS3-TED","full_name":"","num_papers_in_archive":63}],"subtasks":[],"parent_tasks":[{"url":"/task/keyword-spotting","name":"Keyword Spotting"}],"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":4,"of":4,"tagged_in_all":5,"items":[{"url":"/paper/liplearner-customizable-silent-speech","title":"LipLearner: Customizable Silent Speech Interactions on Mobile Devices","date":"2023-02-12","arxiv_id":"2302.05907","repositories_listed":1,"syntology":null},{"url":"/paper/visual-keyword-spotting-with-attention","title":"Visual Keyword Spotting with Attention","date":"2021-10-29","arxiv_id":"2110.15957","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-wake-words-audio-visual-keyword","title":"Seeing wake words: Audio-visual Keyword Spotting","date":"2020-09-02","arxiv_id":"2009.01225","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-keyword-spotting-for-visual-speech","title":"Zero-shot keyword spotting for visual speech recognition in-the-wild","date":"2018-07-23","arxiv_id":"1807.08469","repositories_listed":1,"syntology":null}],"syntology_records":0,"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"}}