{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/grid","name":"GRID Dataset","full_name":null,"description_markdown":"The QMUL underGround Re-IDentification (**GRID**) dataset contains 250 pedestrian image pairs. Each pair contains two images of the same individual seen from different camera views. All images are captured from 8 disjoint camera views installed in a busy underground station. The figures beside show a snapshot of each of the camera views of the station and sample images in the dataset. The dataset is challenging due to variations of pose, colours, lighting changes; as well as poor image quality caused by low spatial resolution.\r\n\r\nSource: [https://personal.ie.cuhk.edu.hk/~ccloy/downloads_qmul_underground_reid.html](https://personal.ie.cuhk.edu.hk/~ccloy/downloads_qmul_underground_reid.html)","description_withheld":null,"homepage":"https://personal.ie.cuhk.edu.hk/~ccloy/downloads_qmul_underground_reid.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"task","url":null,"datasets_with_task":"/datasets/task/task"},{"name":"Speech Enhancement","url":"/task/speech-enhancement","datasets_with_task":"/datasets/task/speech-enhancement"},{"name":"Speech Separation","url":"/task/speech-separation","datasets_with_task":"/datasets/task/speech-separation"},{"name":"Lipreading","url":"/task/lipreading","datasets_with_task":"/datasets/task/lipreading"},{"name":"Speaker-Specific Lip to Speech Synthesis","url":"/task/speaker-specific-lip-to-speech-synthesis","datasets_with_task":"/datasets/task/speaker-specific-lip-to-speech-synthesis"},{"name":"Lip Reading","url":"/task/lip-reading","datasets_with_task":"/datasets/task/lip-reading"}],"languages":[{"name":"Italian","url":"/datasets/language/italian"}],"variants":["GRID corpus (mixed-speech)","GRID Dataset"],"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/lipreading-on-grid-corpus-mixed-speech","task":"Lipreading","dataset_variant":"GRID corpus (mixed-speech)","rows":5,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"CTC/Attention","paper":"/paper/visual-speech-recognition-for-multiple","metrics":{"Word Error Rate (WER)":"1.2"},"code_links":[{"title":"mpc001/Visual_Speech_Recognition_for_Multiple_Languages","url":"https://github.com/mpc001/Visual_Speech_Recognition_for_Multiple_Languages"},{"title":"david-gimeno/lip-rtve","url":"https://github.com/david-gimeno/lip-rtve"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on","task":"Speaker-Specific Lip to Speech Synthesis","dataset_variant":"GRID corpus (mixed-speech)","rows":2,"metrics":["ESTOI","PESQ","STOI"],"first_row_in_archive_order":{"model":"Visual Voice Memory","paper":"/paper/speech-reconstruction-with-reminiscent-sound","metrics":{"ESTOI":"0.579","PESQ":"1.984","STOI":"0.738"},"code_links":[{"title":"joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory","url":"https://github.com/joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-separation-on-grid-corpus-mixed-speech","task":"Speech Separation","dataset_variant":"GRID corpus (mixed-speech)","rows":2,"metrics":["SDR"],"first_row_in_archive_order":{"model":"","paper":"/paper/midi-multi-instance-diffusion-for-single","metrics":{"SDR":"9.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/lip-reading-on-grid-corpus-mixed-speech","task":"Lip Reading","dataset_variant":"GRID corpus (mixed-speech)","rows":1,"metrics":["WER"],"first_row_in_archive_order":{"model":"Lip2Wav","paper":"/paper/learning-individual-speaking-styles-for","metrics":{"WER":"14.08"},"code_links":[{"title":"Rudrabha/Lip2Wav","url":"https://github.com/Rudrabha/Lip2Wav"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-enhancement-on-grid-corpus-mixed","task":"Speech Enhancement","dataset_variant":"GRID corpus (mixed-speech)","rows":1,"metrics":["PESQ"],"first_row_in_archive_order":{"model":"Audio-Visual concat-ref","paper":"/paper/face-landmark-based-speaker-independent-audio","metrics":{"PESQ":"2.70"},"code_links":[{"title":"dr-pato/audio_visual_speech_enhancement","url":"https://github.com/dr-pato/audio_visual_speech_enhancement"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":9,"of":9,"counts":{"papers_with_a_benchmark_row":9,"with_a_code_link":6,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":9,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/midi-multi-instance-diffusion-for-single","slug":"midi-multi-instance-diffusion-for-single","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","date":"2024-12-04","arxiv_id":"2412.03558","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/visual-speech-recognition-for-multiple","slug":"visual-speech-recognition-for-multiple","title":"Visual Speech Recognition for Multiple Languages in the Wild","date":"2022-02-26","arxiv_id":"2202.13084","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/speech-reconstruction-with-reminiscent-sound","slug":"speech-reconstruction-with-reminiscent-sound","title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","date":"2021-11-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-individual-speaking-styles-for","slug":"learning-individual-speaking-styles-for","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","date":"2020-05-17","arxiv_id":"2005.08209","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Rudrabha/Lip2Wav"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-individual-speaking-styles-for#ran","syntology_url":"https://syntology.ai/paper/2005.08209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08209"}}}},{"paper":"/paper/can-we-read-speech-beyond-the-lips-rethinking","slug":"can-we-read-speech-beyond-the-lips-rethinking","title":"Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition","date":"2020-03-06","arxiv_id":"2003.03206","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/face-landmark-based-speaker-independent-audio","slug":"face-landmark-based-speaker-independent-audio","title":"Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments","date":"2018-11-06","arxiv_id":"1811.02480","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/lcanet-end-to-end-lipreading-with-cascaded","slug":"lcanet-end-to-end-lipreading-with-cascaded","title":"LCANet: End-to-End Lipreading with Cascaded Attention-CTC","date":"2018-03-13","arxiv_id":"1803.04988","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lip-reading-sentences-in-the-wild","slug":"lip-reading-sentences-in-the-wild","title":"Lip Reading Sentences in the Wild","date":"2016-11-16","arxiv_id":"1611.05358","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lipnet-end-to-end-sentence-level-lipreading","slug":"lipnet-end-to-end-sentence-level-lipreading","title":"LipNet: End-to-End Sentence-level Lipreading","date":"2016-11-05","arxiv_id":"1611.01599","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["rizkiarm/LipNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lipnet-end-to-end-sentence-level-lipreading#ran","syntology_url":"https://syntology.ai/paper/1611.01599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01599"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/midi-multi-instance-diffusion-for-single","slug":"midi-multi-instance-diffusion-for-single","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","date":"2024-12-04","arxiv_id":"2412.03558","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/visual-speech-recognition-for-multiple","slug":"visual-speech-recognition-for-multiple","title":"Visual Speech Recognition for Multiple Languages in the Wild","date":"2022-02-26","arxiv_id":"2202.13084","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/speech-reconstruction-with-reminiscent-sound","slug":"speech-reconstruction-with-reminiscent-sound","title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","date":"2021-11-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-individual-speaking-styles-for","slug":"learning-individual-speaking-styles-for","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","date":"2020-05-17","arxiv_id":"2005.08209","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Rudrabha/Lip2Wav"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-individual-speaking-styles-for#ran","syntology_url":"https://syntology.ai/paper/2005.08209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08209"}}}},{"paper":"/paper/can-we-read-speech-beyond-the-lips-rethinking","slug":"can-we-read-speech-beyond-the-lips-rethinking","title":"Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition","date":"2020-03-06","arxiv_id":"2003.03206","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/face-landmark-based-speaker-independent-audio","slug":"face-landmark-based-speaker-independent-audio","title":"Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments","date":"2018-11-06","arxiv_id":"1811.02480","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/lcanet-end-to-end-lipreading-with-cascaded","slug":"lcanet-end-to-end-lipreading-with-cascaded","title":"LCANet: End-to-End Lipreading with Cascaded Attention-CTC","date":"2018-03-13","arxiv_id":"1803.04988","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lip-reading-sentences-in-the-wild","slug":"lip-reading-sentences-in-the-wild","title":"Lip Reading Sentences in the Wild","date":"2016-11-16","arxiv_id":"1611.05358","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lipnet-end-to-end-sentence-level-lipreading","slug":"lipnet-end-to-end-sentence-level-lipreading","title":"LipNet: End-to-End Sentence-level Lipreading","date":"2016-11-05","arxiv_id":"1611.01599","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["rizkiarm/LipNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lipnet-end-to-end-sentence-level-lipreading#ran","syntology_url":"https://syntology.ai/paper/1611.01599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01599"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/grid/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/grid/papers/ran/1","json":"/dataset/grid/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":24,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"0fd0b2e343799ae332c5c126419095778b7a39e4b4dc7fea5560e026420c5aa4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}