{"url":"/task/audio-visual-synchronization","name":"Audio-Visual Synchronization","slug":"audio-visual-synchronization","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"},{"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":32,"papers_with_code":11,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/acappella","name":"Acappella","full_name":"","num_papers_in_archive":5},{"url":"/dataset/vggsound-sparse","name":"VGGSound-Sparse","full_name":"","num_papers_in_archive":5},{"url":"/dataset/avsync15","name":"AVSync15","full_name":"","num_papers_in_archive":2},{"url":"/dataset/avs-benchmark","name":"AVS Benchmark","full_name":"Audio-Visual Synchrony Benchmark","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":11,"of":11,"tagged_in_all":32,"items":[{"url":"/paper/synchformer-efficient-synchronization-from","title":"Synchformer: Efficient Synchronization from Sparse Cues","date":"2024-01-29","arxiv_id":"2401.16423","repositories_listed":2,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/multimodal-transformer-distillation-for-audio","title":"Multimodal Transformer Distillation for Audio-Visual Synchronization","date":"2022-10-27","arxiv_id":"2210.15563","repositories_listed":2,"syntology":null},{"url":"/paper/sparse-in-space-and-time-audio-visual","title":"Sparse in Space and Time: Audio-visual Synchronisation with Trainable Selectors","date":"2022-10-13","arxiv_id":"2210.07055","repositories_listed":2,"syntology":null},{"url":"/paper/cogenav-versatile-audio-visual-representation","title":"CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization","date":"2025-05-06","arxiv_id":"2505.03186","repositories_listed":1,"syntology":null},{"url":"/paper/taming-multimodal-joint-training-for-high","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","date":"2024-12-19","arxiv_id":"2412.15322","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/musetalk-real-time-high-quality-lip","title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","date":"2024-10-14","arxiv_id":"2410.10122","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":8}},{"url":"/paper/explicit-correlation-learning-for","title":"Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection","date":"2024-04-30","arxiv_id":"2404.19171","repositories_listed":1,"syntology":null},{"url":"/paper/peavs-perceptual-evaluation-of-audio-visual","title":"PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores","date":"2024-04-10","arxiv_id":"2404.07336","repositories_listed":1,"syntology":null},{"url":"/paper/target-active-speaker-detection-with-audio","title":"Target Active Speaker Detection with Audio-visual Cues","date":"2023-05-22","arxiv_id":"2305.12831","repositories_listed":1,"syntology":null},{"url":"/paper/vocalist-an-audio-visual-synchronisation","title":"VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices","date":"2022-04-05","arxiv_id":"2204.02090","repositories_listed":1,"syntology":null},{"url":"/paper/neural-pitch-shifting-and-time-stretching","title":"Neural Pitch-Shifting and Time-Stretching with Controllable LPCNet","date":"2021-10-05","arxiv_id":"2110.02360","repositories_listed":1,"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"},"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"}}