{"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/vgg-sound","name":"VGG-Sound","full_name":null,"description_markdown":"Consists of more than 210k videos for 310 audio classes.\r\n\r\nSource: [VGGSound: A Large-scale Audio-Visual Dataset](/paper/vggsound-a-large-scale-audio-visual-dataset)","description_withheld":null,"homepage":"http://www.robots.ox.ac.uk/~vgg/data/vggsound/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/vggsound-a-large-scale-audio-visual-dataset","title":"VGGSound: A Large-scale Audio-Visual Dataset","first_author":"Honglie Chen","url":null},"license":{"name":"CC-BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Audio Classification","url":"/task/audio-classification","datasets_with_task":"/datasets/task/audio-classification"},{"name":"Speaker Verification","url":"/task/speaker-verification","datasets_with_task":"/datasets/task/speaker-verification"},{"name":"Zero-shot Audio Classification","url":"/task/zero-shot-audio-classification","datasets_with_task":"/datasets/task/zero-shot-audio-classification"},{"name":"Multi-modal Classification","url":"/task/multi-modal-classification","datasets_with_task":"/datasets/task/multi-modal-classification"},{"name":"Speaker Recognition","url":"/task/speaker-recognition","datasets_with_task":"/datasets/task/speaker-recognition"},{"name":"Video-to-Sound Generation","url":"/task/video-to-sound-generation","datasets_with_task":"/datasets/task/video-to-sound-generation"}],"languages":[],"variants":["VGG-Sound","VGGSound"],"data_loaders":[],"num_papers_in_archive":211,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/audio-classification-on-vggsound","task":"Audio Classification","dataset_variant":"VGGSound","rows":23,"metrics":["Top 1 Accuracy","Top 5 Accuracy","Mean AP","AUC","d-prime"],"first_row_in_archive_order":{"model":"Mirasol3B","paper":"/paper/mirasol3b-a-multimodal-autoregressive-model","metrics":{"Top 1 Accuracy":"69.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-to-sound-generation-on-vgg-sound","task":"Video-to-Sound Generation","dataset_variant":"VGG-Sound","rows":8,"metrics":["FAD","FD","KLD"],"first_row_in_archive_order":{"model":"MMAudio-S-16kHz","paper":"/paper/taming-multimodal-joint-training-for-high","metrics":{"FAD":"0.79","FD":"5.22"},"code_links":[{"title":"hkchengrex/MMAudio","url":"https://github.com/hkchengrex/MMAudio"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-modal-classification-on-vgg-sound","task":"Multi-modal Classification","dataset_variant":"VGG-Sound","rows":4,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"MMT","paper":"/paper/multiscale-multimodal-transformer-for","metrics":{"Top-1 Accuracy":"66.2","Top-5 Accuracy":"85.7"},"code_links":[]},"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":19,"of":19,"counts":{"papers_with_a_benchmark_row":19,"with_a_code_link":13,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":19,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":8,"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/ca-2st-cross-attention-in-audio-space-and","slug":"ca-2st-cross-attention-in-audio-space-and","title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","date":"2025-03-30","arxiv_id":"2503.23447","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/taming-multimodal-joint-training-for-high","slug":"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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["hkchengrex/MMAudio"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/taming-multimodal-joint-training-for-high#ran","syntology_url":"https://syntology.ai/paper/2412.15322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15322"}}}},{"paper":"/paper/tell-what-you-hear-from-what-you-see-video-to","slug":"tell-what-you-hear-from-what-you-see-video-to","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","date":"2024-11-08","arxiv_id":"2411.05679","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["DragonLiu1995/multimodal-llm-for-audio-gen"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tell-what-you-hear-from-what-you-see-video-to#ran","syntology_url":"https://syntology.ai/paper/2411.05679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05679"}}}},{"paper":"/paper/temporally-aligned-audio-for-video-with","slug":"temporally-aligned-audio-for-video-with","title":"Temporally Aligned Audio for Video with Autoregression","date":"2024-09-20","arxiv_id":"2409.13689","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":6,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["ilpoviertola/V-AURA"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/temporally-aligned-audio-for-video-with#ran","syntology_url":"https://syntology.ai/paper/2409.13689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13689"}}}},{"paper":"/paper/masked-generative-video-to-audio-transformers","slug":"masked-generative-video-to-audio-transformers","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","date":"2024-07-15","arxiv_id":"2407.10387","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/read-watch-and-scream-sound-generation-from","slug":"read-watch-and-scream-sound-generation-from","title":"Read, Watch and Scream! Sound Generation from Text and Video","date":"2024-07-08","arxiv_id":"2407.05551","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":15,"samples_unverified":4,"pointer_only_for_licence":22,"official":{"repos":["naver-ai/rewas"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/read-watch-and-scream-sound-generation-from#ran","syntology_url":"https://syntology.ai/paper/2407.05551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05551"}}}},{"paper":"/paper/frieren-efficient-video-to-audio-generation","slug":"frieren-efficient-video-to-audio-generation","title":"Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching","date":"2024-06-01","arxiv_id":"2406.00320","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":8,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["cyanbx/Frieren-V2A"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/frieren-efficient-video-to-audio-generation#ran","syntology_url":"https://syntology.ai/paper/2406.00320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00320"}}}},{"paper":"/paper/equiav-leveraging-equivariance-for-audio","slug":"equiav-leveraging-equivariance-for-audio","title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning","date":"2024-03-14","arxiv_id":"2403.09502","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":6,"samples_constructed":4,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":{"repos":["jongsuk1/equiav"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/equiav-leveraging-equivariance-for-audio#ran","syntology_url":"https://syntology.ai/paper/2403.09502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09502"}}}},{"paper":"/paper/mirasol3b-a-multimodal-autoregressive-model","slug":"mirasol3b-a-multimodal-autoregressive-model","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","date":"2023-11-09","arxiv_id":"2311.05698","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/v2a-mapper-a-lightweight-solution-for-vision","slug":"v2a-mapper-a-lightweight-solution-for-vision","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","date":"2023-08-18","arxiv_id":"2308.09300","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}}}},{"paper":"/paper/multiscale-audio-spectrogram-transformer-for","slug":"multiscale-audio-spectrogram-transformer-for","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","date":"2023-03-19","arxiv_id":"2303.10757","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/audiovisual-masked-autoencoders","slug":"audiovisual-masked-autoencoders","title":"Audiovisual Masked Autoencoders","date":"2022-12-09","arxiv_id":"2212.05922","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/play-it-back-iterative-attention-for-audio","slug":"play-it-back-iterative-attention-for-audio","title":"Play It Back: Iterative Attention for Audio Recognition","date":"2022-10-20","arxiv_id":"2210.11328","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/contrastive-audio-visual-masked-autoencoder","slug":"contrastive-audio-visual-masked-autoencoder","title":"Contrastive Audio-Visual Masked Autoencoder","date":"2022-10-02","arxiv_id":"2210.07839","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["yuangongnd/cav-mae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/contrastive-audio-visual-masked-autoencoder#ran","syntology_url":"https://syntology.ai/paper/2210.07839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07839"}}}},{"paper":"/paper/avt-audio-video-transformer-for-multimodal","slug":"avt-audio-video-transformer-for-multimodal","title":"AVT: Audio-Video Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/multiscale-multimodal-transformer-for","slug":"multiscale-multimodal-transformer-for","title":"Multiscale Multimodal Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/uavm-a-unified-model-for-audio-visual","slug":"uavm-a-unified-model-for-audio-visual","title":"UAVM: Towards Unifying Audio and Visual Models","date":"2022-07-29","arxiv_id":"2208.00061","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["YuanGongND/uavm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/uavm-a-unified-model-for-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2208.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00061"}}}},{"paper":"/paper/attention-bottlenecks-for-multimodal-fusion","slug":"attention-bottlenecks-for-multimodal-fusion","title":"Attention Bottlenecks for Multimodal Fusion","date":"2021-06-30","arxiv_id":"2107.00135","rows_on_this_dataset":3,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/ca-2st-cross-attention-in-audio-space-and","slug":"ca-2st-cross-attention-in-audio-space-and","title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","date":"2025-03-30","arxiv_id":"2503.23447","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/taming-multimodal-joint-training-for-high","slug":"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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["hkchengrex/MMAudio"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/taming-multimodal-joint-training-for-high#ran","syntology_url":"https://syntology.ai/paper/2412.15322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15322"}}}},{"paper":"/paper/tell-what-you-hear-from-what-you-see-video-to","slug":"tell-what-you-hear-from-what-you-see-video-to","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","date":"2024-11-08","arxiv_id":"2411.05679","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["DragonLiu1995/multimodal-llm-for-audio-gen"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tell-what-you-hear-from-what-you-see-video-to#ran","syntology_url":"https://syntology.ai/paper/2411.05679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05679"}}}},{"paper":"/paper/temporally-aligned-audio-for-video-with","slug":"temporally-aligned-audio-for-video-with","title":"Temporally Aligned Audio for Video with Autoregression","date":"2024-09-20","arxiv_id":"2409.13689","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":6,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["ilpoviertola/V-AURA"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/temporally-aligned-audio-for-video-with#ran","syntology_url":"https://syntology.ai/paper/2409.13689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13689"}}}},{"paper":"/paper/masked-generative-video-to-audio-transformers","slug":"masked-generative-video-to-audio-transformers","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","date":"2024-07-15","arxiv_id":"2407.10387","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/read-watch-and-scream-sound-generation-from","slug":"read-watch-and-scream-sound-generation-from","title":"Read, Watch and Scream! Sound Generation from Text and Video","date":"2024-07-08","arxiv_id":"2407.05551","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":15,"samples_unverified":4,"pointer_only_for_licence":22,"official":{"repos":["naver-ai/rewas"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/read-watch-and-scream-sound-generation-from#ran","syntology_url":"https://syntology.ai/paper/2407.05551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05551"}}}},{"paper":"/paper/frieren-efficient-video-to-audio-generation","slug":"frieren-efficient-video-to-audio-generation","title":"Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching","date":"2024-06-01","arxiv_id":"2406.00320","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":8,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["cyanbx/Frieren-V2A"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/frieren-efficient-video-to-audio-generation#ran","syntology_url":"https://syntology.ai/paper/2406.00320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00320"}}}},{"paper":"/paper/equiav-leveraging-equivariance-for-audio","slug":"equiav-leveraging-equivariance-for-audio","title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning","date":"2024-03-14","arxiv_id":"2403.09502","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":6,"samples_constructed":4,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":{"repos":["jongsuk1/equiav"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/equiav-leveraging-equivariance-for-audio#ran","syntology_url":"https://syntology.ai/paper/2403.09502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09502"}}}},{"paper":"/paper/mirasol3b-a-multimodal-autoregressive-model","slug":"mirasol3b-a-multimodal-autoregressive-model","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","date":"2023-11-09","arxiv_id":"2311.05698","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/v2a-mapper-a-lightweight-solution-for-vision","slug":"v2a-mapper-a-lightweight-solution-for-vision","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","date":"2023-08-18","arxiv_id":"2308.09300","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}}}},{"paper":"/paper/multiscale-audio-spectrogram-transformer-for","slug":"multiscale-audio-spectrogram-transformer-for","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","date":"2023-03-19","arxiv_id":"2303.10757","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/audiovisual-masked-autoencoders","slug":"audiovisual-masked-autoencoders","title":"Audiovisual Masked Autoencoders","date":"2022-12-09","arxiv_id":"2212.05922","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/play-it-back-iterative-attention-for-audio","slug":"play-it-back-iterative-attention-for-audio","title":"Play It Back: Iterative Attention for Audio Recognition","date":"2022-10-20","arxiv_id":"2210.11328","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/contrastive-audio-visual-masked-autoencoder","slug":"contrastive-audio-visual-masked-autoencoder","title":"Contrastive Audio-Visual Masked Autoencoder","date":"2022-10-02","arxiv_id":"2210.07839","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["yuangongnd/cav-mae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/contrastive-audio-visual-masked-autoencoder#ran","syntology_url":"https://syntology.ai/paper/2210.07839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07839"}}}},{"paper":"/paper/avt-audio-video-transformer-for-multimodal","slug":"avt-audio-video-transformer-for-multimodal","title":"AVT: Audio-Video Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/multiscale-multimodal-transformer-for","slug":"multiscale-multimodal-transformer-for","title":"Multiscale Multimodal Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/uavm-a-unified-model-for-audio-visual","slug":"uavm-a-unified-model-for-audio-visual","title":"UAVM: Towards Unifying Audio and Visual Models","date":"2022-07-29","arxiv_id":"2208.00061","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["YuanGongND/uavm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/uavm-a-unified-model-for-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2208.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00061"}}}},{"paper":"/paper/attention-bottlenecks-for-multimodal-fusion","slug":"attention-bottlenecks-for-multimodal-fusion","title":"Attention Bottlenecks for Multimodal Fusion","date":"2021-06-30","arxiv_id":"2107.00135","rows_on_this_dataset":3,"code_links":1,"syntology":null}],"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/dataset/vgg-sound/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/vgg-sound/papers/ran/1","json":"/dataset/vgg-sound/papers/ran/1.json","rows":8}],"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":9,"samples_harvested":97,"samples_ran":75,"samples_constructed":6,"samples_ran_checked":39,"samples_ran_instrument_failed":36,"samples_unverified":22,"pointer_only_for_licence":40,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":8,"papers_with_a_run_with_no_instrument_failure":8,"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":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/video-to-sound-generation-on-vgg-sound","since_archive":"/sota/video-to-sound-generation-on-vgg-sound#since-judged","papers_judged":4,"placed":0}]},"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":"0462a9f15c11cad014947774d18fc0cf0f5088ffbe831ebf18531cf82dd0ca85","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}