{"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":"/task/video-synchronization","name":"Video Synchronization","slug":"video-synchronization","description_markdown":null,"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":30,"papers_with_code":9,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/vggsound-sparse","name":"VGGSound-Sparse","full_name":"","num_papers_in_archive":5},{"url":"/dataset/msu-video-alignment-and-retrieval-benchmark","name":"MSU Video Alignment and Retrieval Benchmark Suite","full_name":"MSU Video Alignment and Retrieval Benchmark Suite","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/video","name":"Video"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":30,"of":30,"of_with_code":9,"tagged_in_all":30,"counts":{"archive_papers_tagged":30,"with_a_code_link":9,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":30,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":1,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/190513313","slug":"190513313","title":"Technical Report of the Video Event Reconstruction and Analysis (VERA) System -- Shooter Localization, Models, Interface, and Beyond","date":"2019-05-26","arxiv_id":"1905.13313","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-audio-and-pose-a-general-purpose","slug":"beyond-audio-and-pose-a-general-purpose","title":"Beyond Audio and Pose: A General-Purpose Framework for Video Synchronization","date":"2025-06-19","arxiv_id":"2506.15937","repositories_listed":1,"syntology":null},{"url":"/paper/drift-open-dataset-a-drone-derived","slug":"drift-open-dataset-a-drone-derived","title":"DRIFT open dataset: A drone-derived intelligence for traffic analysis in urban environmen","date":"2025-04-15","arxiv_id":"2504.11019","repositories_listed":1,"syntology":null},{"url":"/paper/foleycrafter-bring-silent-videos-to-life-with","slug":"foleycrafter-bring-silent-videos-to-life-with","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","date":"2024-07-01","arxiv_id":"2407.01494","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/foleycrafter-bring-silent-videos-to-life-with#ran","syntology_url":"https://syntology.ai/paper/2407.01494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01494"}},"official":{"repos":["open-mmlab/foleycrafter"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/posesync-robust-pose-based-video","slug":"posesync-robust-pose-based-video","title":"PoseSync: Robust pose based video synchronization","date":"2023-08-24","arxiv_id":"2308.12600","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/posesync-robust-pose-based-video#ran","syntology_url":"https://syntology.ai/paper/2308.12600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12600"}},"official":{"repos":["infocusp/posesync"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-learning-based-stereo-camera-multi-video","slug":"deep-learning-based-stereo-camera-multi-video","title":"Deep learning-based stereo camera multi-video synchronization","date":"2023-03-22","arxiv_id":"2303.12916","repositories_listed":1,"syntology":null},{"url":"/paper/a-subjective-study-of-the-perceptual","slug":"a-subjective-study-of-the-perceptual","title":"A subjective study of the perceptual acceptability of audio-video desynchronization in sports videos","date":"2022-12-03","arxiv_id":"2212.01686","repositories_listed":1,"syntology":null},{"url":"/paper/representation-learning-via-global-temporal","slug":"representation-learning-via-global-temporal","title":"Representation Learning via Global Temporal Alignment and Cycle-Consistency","date":"2021-05-11","arxiv_id":"2105.05217","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/representation-learning-via-global-temporal#ran","syntology_url":"https://syntology.ai/paper/2105.05217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05217"}},"official":{"repos":["hadjisma/VideoAlignment"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rolling-shutter-camera-synchronization-with","slug":"rolling-shutter-camera-synchronization-with","title":"Rolling Shutter Camera Synchronization with Sub-millisecond Accuracy","date":"2019-02-28","arxiv_id":"1902.11084","repositories_listed":1,"syntology":null},{"url":null,"slug":"aligndit-multimodal-aligned-diffusion","title":"AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation","date":"2025-04-29","arxiv_id":"2504.20629","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-10005","title":"Multimodal Cinematic Video Synthesis Using Text-to-Image and Audio Generation Models","date":"2025-04-06","arxiv_id":"2506.10005","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnitalker-real-time-text-driven-talking-head","title":"OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication","date":"2025-04-03","arxiv_id":"2504.02433","repositories_listed":0,"syntology":null},{"url":null,"slug":"av-link-temporally-aligned-diffusion-features","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","date":"2024-12-19","arxiv_id":"2412.15191","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-video-diffusion-consistent","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","date":"2024-05-27","arxiv_id":"2405.17414","repositories_listed":0,"syntology":null},{"url":null,"slug":"dance-any-beat-blending-beats-with-visuals-in","title":"Dance Any Beat: Blending Beats with Visuals in Dance Video Generation","date":"2024-05-15","arxiv_id":"2405.09266","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-talking-face-video-generation","title":"Context-aware Talking Face Video Generation","date":"2024-02-28","arxiv_id":"2402.18092","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-alignment-using-unsupervised-learning","title":"Video alignment using unsupervised learning of local and global features","date":"2023-04-13","arxiv_id":"2304.06841","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeformer-modality-preserving-embedding-for","title":"ModEFormer: Modality-Preserving Embedding for Audio-Video Synchronization using Transformers","date":"2023-03-21","arxiv_id":"2303.11551","repositories_listed":0,"syntology":null},{"url":null,"slug":"bronchoscopic-video-synchronization-for","title":"Bronchoscopic video synchronization for interactive multimodal inspection of bronchial lesions","date":"2023-03-20","arxiv_id":"2303.11258","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-automated-machine-translation-to","title":"Applying Automated Machine Translation to Educational Video Courses","date":"2023-01-09","arxiv_id":"2301.03141","repositories_listed":0,"syntology":null},{"url":null,"slug":"revise-self-supervised-speech-resynthesis-1","title":"ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sidgan-high-resolution-dubbed-video","title":"SIDGAN: High-Resolution Dubbed Video Generation via Shift-Invariant Learning","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/revise-self-supervised-speech-resynthesis","slug":"revise-self-supervised-speech-resynthesis","title":"ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement","date":"2022-12-21","arxiv_id":"2212.11377","repositories_listed":0,"syntology":null},{"url":null,"slug":"sub-millisecond-video-synchronization-of","title":"Sub-millisecond Video Synchronization of Multiple Android Smartphones","date":"2021-07-02","arxiv_id":"2107.00987","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-audio-video-synchronization","title":"Detection of Audio-Video Synchronization Errors Via Event Detection","date":"2021-04-20","arxiv_id":"2104.10116","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-for-audio-visual","title":"Self-supervised learning for audio-visual speaker diarization","date":"2020-02-13","arxiv_id":"2002.05314","repositories_listed":0,"syntology":null},{"url":"/paper/multi-task-learning-for-audio-visual-active","slug":"multi-task-learning-for-audio-visual-active","title":"Multi-Task Learning for Audio Visual Active Speaker Detection","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"perfect-match-improved-cross-modal-embeddings","title":"Perfect match: Improved cross-modal embeddings for audio-visual synchronisation","date":"2018-09-21","arxiv_id":"1809.08001","repositories_listed":0,"syntology":null},{"url":"/paper/accurate-method-of-temporal-shift-estimation","slug":"accurate-method-of-temporal-shift-estimation","title":"ACCURATE METHOD OF TEMPORAL-SHIFT ESTIMATION FOR 3D VIDEO","date":"2018-06-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robust-video-synchronization-without","title":"Learning Robust Video Synchronization without Annotations","date":"2016-10-19","arxiv_id":"1610.05985","repositories_listed":0,"syntology":null}],"syntology_records":3,"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"},"key_notes":{"n_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'","n_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_where_code_ran":3,"papers_where_code_ran_first_page":"/task/video-synchronization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/video-synchronization/papers/ran/1","json":"/task/video-synchronization/papers/ran/1.json","rows":3}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"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"},"record_sha256":"2e2a286293d162bb10a23dcb4a66bfadcba42fd19f2fa2fde386fa86e15ef70f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}