{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/contrastive-audio-visual-masked-autoencoder","title":"Contrastive Audio-Visual Masked Autoencoder","arxiv_id":"2210.07839","date":"2022-10-02","proceeding":null,"authors":["Yuan Gong","Andrew Rouditchenko","Alexander H. Liu","David Harwath","Leonid Karlinsky","Hilde Kuehne","James Glass"],"abstract":"In this paper, we first extend the recent Masked Auto-Encoder (MAE) model from a single modality to audio-visual multi-modalities. Subsequently, we propose the Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE) by combining contrastive learning and masked data modeling, two major self-supervised learning frameworks, to learn a joint and coordinated audio-visual representation. Our experiments show that the contrastive audio-visual correspondence learning objective not only enables the model to perform audio-visual retrieval tasks, but also helps the model learn a better joint representation. As a result, our fully self-supervised pretrained CAV-MAE achieves a new SOTA accuracy of 65.9% on VGGSound, and is comparable with the previous best supervised pretrained model on AudioSet in the audio-visual event classification task. Code and pretrained models are at https://github.com/yuangongnd/cav-mae.","url_abs":"https://arxiv.org/abs/2210.07839v4","url_pdf":"https://arxiv.org/pdf/2210.07839v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"contrastive-audio-visual-masked-autoencoder","repo_url":"https://github.com/yuangongnd/cav-mae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"audio-tagging","task_name":"Audio Tagging"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"multi-modal-classification","task_name":"Multi-modal Classification"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"sound-prompted-semantic-segmentation","task_name":"Sound Prompted Semantic Segmentation"},{"task_slug":"speech-prompted-semantic-segmentation","task_name":"Speech Prompted Semantic Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-classification-on-audioset","task":"Audio Classification","dataset":"AudioSet","model":"CAV-MAE (Audio-Visual)","rank_in_archive_order":6,"of":51,"metrics":{"Test mAP":"0.512"},"uses_additional_data":true},{"leaderboard":"/sota/audio-classification-on-audioset","task":"Audio Classification","dataset":"AudioSet","model":"CAV-MAE (Audio-Only)","rank_in_archive_order":34,"of":51,"metrics":{"Test mAP":"0.466"},"uses_additional_data":true},{"leaderboard":"/sota/audio-classification-on-audioset","task":"Audio Classification","dataset":"AudioSet","model":"CAV-MAE (Visual-Only)","rank_in_archive_order":49,"of":51,"metrics":{"Test mAP":"0.262"},"uses_additional_data":true},{"leaderboard":"/sota/audio-classification-on-vggsound","task":"Audio Classification","dataset":"VGGSound","model":"CAV-MAE (Audio-Visual)","rank_in_archive_order":8,"of":23,"metrics":{"Top 1 Accuracy":"65.9"},"uses_additional_data":true},{"leaderboard":"/sota/audio-classification-on-vggsound","task":"Audio Classification","dataset":"VGGSound","model":"CAV-MAE (Audio-Only)","rank_in_archive_order":13,"of":23,"metrics":{"Top 1 Accuracy":"59.5"},"uses_additional_data":true},{"leaderboard":"/sota/audio-tagging-on-audioset","task":"Audio Tagging","dataset":"AudioSet","model":"CAV-MAE (Audio-Visual)","rank_in_archive_order":1,"of":11,"metrics":{"mean average precision":"0.512"},"uses_additional_data":true},{"leaderboard":"/sota/audio-tagging-on-audioset","task":"Audio Tagging","dataset":"AudioSet","model":"CAV-MAE (Audio-Only)","rank_in_archive_order":9,"of":11,"metrics":{"mean average precision":"0.466"},"uses_additional_data":true},{"leaderboard":"/sota/multi-modal-classification-on-audioset","task":"Multi-modal Classification","dataset":"AudioSet","model":"CAV-MAE","rank_in_archive_order":1,"of":2,"metrics":{"Average mAP":"0.512"},"uses_additional_data":true},{"leaderboard":"/sota/multi-modal-classification-on-vgg-sound","task":"Multi-modal Classification","dataset":"VGG-Sound","model":"CAV-MAE (Audio-Visual)","rank_in_archive_order":2,"of":4,"metrics":{"Top-1 Accuracy":"65.9"},"uses_additional_data":true},{"leaderboard":"/sota/sound-prompted-semantic-segmentation-on","task":"Sound Prompted Semantic Segmentation","dataset":"ADE20K","model":"CAVMAE","rank_in_archive_order":2,"of":4,"metrics":{"mAP":"26.0","mIoU":"17.0"},"uses_additional_data":false},{"leaderboard":"/sota/speech-prompted-semantic-segmentation-on","task":"Speech Prompted Semantic Segmentation","dataset":"ADE20K","model":"CAVMAE","rank_in_archive_order":3,"of":4,"metrics":{"mAP":"27.2","mIoU":"19.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.07839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07839"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/yuangongnd/cav-mae","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"91c9a9d5d1a63e94","entry":"CAVMAE","repo":"yuangongnd/cav-mae","repo_kind":"official","path":"src/models/cav_mae.py","file_url":"https://github.com/yuangongnd/cav-mae/blob/HEAD/src/models/cav_mae.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"91c9a9d5d1a63e94"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}