{"url":"/sota/audio-classification-on-audioset","task":{"name":"Audio Classification","url":"/task/audio-classification","note":null},"dataset":{"name":"AudioSet","url":"/dataset/audioset"},"category":"Audio","categories":["Audio"],"category_note":null,"description":"**Audio Classification** is a machine learning task that involves identifying and tagging audio signals into different classes or categories. The goal of audio classification is to enable machines to automatically recognize and distinguish between different types of audio, such as music, speech, and environmental sounds.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Test mAP","AUC","d-prime"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Test mAP":"higher","AUC":"higher","d-prime":null}},"counts":{"rows":51,"rows_with_code":40,"rows_with_paper_page":47,"rows_dated":48,"rows_using_additional_data":20},"rows":[{"rank_in_archive_order":1,"model":"OmniVec2","metrics":{"Test mAP":"0.558"},"uses_additional_data":true,"paper_date":"2024-01-01","paper":"/paper/omnivec2-a-novel-transformer-based-network","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Srivastava_OmniVec2_-_A_Novel_Transformer_based_Network_for_Large_Scale_CVPR_2024_paper.html","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"OmniVec","metrics":{"Test mAP":"0.548"},"uses_additional_data":true,"paper_date":"2023-11-07","paper":"/paper/omnivec-learning-robust-representations-with","paper_url":"https://arxiv.org/abs/2311.05709v1","paper_title":"OmniVec: Learning robust representations with cross modal sharing","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"EquiAV","metrics":{"Test mAP":"0.546"},"uses_additional_data":false,"paper_date":"2024-03-14","paper":"/paper/equiav-leveraging-equivariance-for-audio","paper_url":"https://arxiv.org/abs/2403.09502v2","paper_title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning","code":"https://github.com/jongsuk1/equiav","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":7,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"MAViL (Audio-Visual, single)","metrics":{"Test mAP":"0.533"},"uses_additional_data":true,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"Audiovisual Masked Autoencoder (Audiovisual, Single)","metrics":{"Test mAP":"0.518"},"uses_additional_data":false,"paper_date":"2022-12-09","paper":"/paper/audiovisual-masked-autoencoders","paper_url":"https://arxiv.org/abs/2212.05922v3","paper_title":"Audiovisual Masked Autoencoders","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/av_mae","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"CAV-MAE (Audio-Visual)","metrics":{"Test mAP":"0.512"},"uses_additional_data":true,"paper_date":"2022-10-02","paper":"/paper/contrastive-audio-visual-masked-autoencoder","paper_url":"https://arxiv.org/abs/2210.07839v4","paper_title":"Contrastive Audio-Visual Masked Autoencoder","code":"https://github.com/yuangongnd/cav-mae","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"BEATs (Audio-only, Ensemble)","metrics":{"Test mAP":"0.506"},"uses_additional_data":false,"paper_date":"2022-12-18","paper":"/paper/beats-audio-pre-training-with-acoustic","paper_url":"https://arxiv.org/abs/2212.09058v1","paper_title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","code":"https://github.com/microsoft/unilm/tree/master/beats","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":15,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"UAVM (Audio + Video)","metrics":{"Test mAP":"0.504"},"uses_additional_data":true,"paper_date":"2022-07-29","paper":"/paper/uavm-a-unified-model-for-audio-visual","paper_url":"https://arxiv.org/abs/2208.00061v2","paper_title":"UAVM: Towards Unifying Audio and Visual Models","code":"https://github.com/YuanGongND/uavm","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":8,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"SSLAM (Audio-Only, Single)","metrics":{"Test mAP":"0.502"},"uses_additional_data":false,"paper_date":"2025-06-13","paper":"/paper/sslam-enhancing-self-supervised-models-with-1","paper_url":"https://arxiv.org/abs/2506.12222v1","paper_title":"SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes","code":"https://github.com/ta012/SSLAM","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"mn40_as (Ensemble)","metrics":{"Test mAP":"0.498"},"uses_additional_data":true,"paper_date":"2022-11-09","paper":"/paper/efficient-large-scale-audio-tagging-via","paper_url":"https://arxiv.org/abs/2211.04772v3","paper_title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","code":"https://github.com/fschmid56/efficientat","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"ATST-C2F(Single)","metrics":{"Test mAP":"0.497"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/self-supervised-audio-teacher-student","paper_url":"https://arxiv.org/abs/2306.04186v2","paper_title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","code":"https://github.com/Audio-WestlakeU/ATST-SED","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"MBT (AS-500K training + Video)","metrics":{"Test mAP":"0.496"},"uses_additional_data":true,"paper_date":"2021-06-30","paper":"/paper/attention-bottlenecks-for-multimodal-fusion","paper_url":"https://arxiv.org/abs/2107.00135v3","paper_title":"Attention Bottlenecks for Multimodal Fusion","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/mbt","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"PaSST (Ensemble)","metrics":{"Test mAP":"0.496"},"uses_additional_data":true,"paper_date":"2021-10-11","paper":"/paper/efficient-training-of-audio-transformers-with","paper_url":"https://arxiv.org/abs/2110.05069v3","paper_title":"Efficient Training of Audio Transformers with Patchout","code":"https://github.com/kkoutini/passt","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"DyMN-L (Audio-Only, Single)","metrics":{"Test mAP":"0.490"},"uses_additional_data":true,"paper_date":"2023-10-24","paper":"/paper/dynamic-convolutional-neural-networks-as","paper_url":"https://arxiv.org/abs/2310.15648v1","paper_title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","code":"https://github.com/fschmid56/efficientat","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"M2D2","metrics":{"Test mAP":"0.490"},"uses_additional_data":false,"paper_date":"2025-03-28","paper":"/paper/m2d2-exploring-general-purpose-audio-language","paper_url":"https://arxiv.org/abs/2503.22104v1","paper_title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","code":"https://github.com/nttcslab/m2d","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"HTS-AT (Ensemble)","metrics":{"Test mAP":"0.487"},"uses_additional_data":true,"paper_date":"2022-02-02","paper":"/paper/hts-at-a-hierarchical-token-semantic-audio","paper_url":"https://arxiv.org/abs/2202.00874v1","paper_title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","code":"https://github.com/retrocirce/hts-audio-transformer","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"BEATs (Audio-only, Single)","metrics":{"Test mAP":"0.486"},"uses_additional_data":false,"paper_date":"2022-12-18","paper":"/paper/beats-audio-pre-training-with-acoustic","paper_url":"https://arxiv.org/abs/2212.09058v1","paper_title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","code":"https://github.com/microsoft/unilm/tree/master/beats","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":15,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"EAT","metrics":{"Test mAP":"0.486"},"uses_additional_data":false,"paper_date":"2024-01-07","paper":"/paper/eat-self-supervised-pre-training-with","paper_url":"https://arxiv.org/abs/2401.03497v1","paper_title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","code":"https://github.com/cwx-worst-one/eat","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":4,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"DTF-AT (Single)","metrics":{"Test mAP":"0.486"},"uses_additional_data":false,"paper_date":"2024-03-24","paper":"/paper/dtf-at-decoupled-time-frequency-audio","paper_url":"https://ojs.aaai.org/index.php/AAAI/article/view/29716","paper_title":"DTF-AT: Decoupled Time-Frequency Audio Transformer for Event Classification","code":"https://github.com/ta012/DTFAT","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"AST (Ensemble)","metrics":{"Test mAP":"0.485"},"uses_additional_data":true,"paper_date":"2021-04-05","paper":"/paper/ast-audio-spectrogram-transformer","paper_url":"https://arxiv.org/abs/2104.01778v3","paper_title":"AST: Audio Spectrogram Transformer","code":"https://github.com/YuanGongND/ast","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"M2D-CLAP/0.7","metrics":{"Test mAP":"0.485"},"uses_additional_data":false,"paper_date":"2024-06-04","paper":"/paper/m2d-clap-masked-modeling-duo-meets-clap-for","paper_url":"https://arxiv.org/abs/2406.02032v1","paper_title":"M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation","code":"https://github.com/nttcslab/m2d","n_code_links":2,"syntology":null},{"rank_in_archive_order":22,"model":"M2D-AS/0.7","metrics":{"Test mAP":"0.485"},"uses_additional_data":false,"paper_date":"2024-04-09","paper":"/paper/masked-modeling-duo-towards-a-universal-audio","paper_url":"https://arxiv.org/abs/2404.06095v1","paper_title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","code":"https://github.com/nttcslab/m2d","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":23,"model":"MAViL (Audio-only, single)","metrics":{"Test mAP":"0.484"},"uses_additional_data":true,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"mn40_as (Single)","metrics":{"Test mAP":"0.483"},"uses_additional_data":true,"paper_date":"2022-11-09","paper":"/paper/efficient-large-scale-audio-tagging-via","paper_url":"https://arxiv.org/abs/2211.04772v3","paper_title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","code":"https://github.com/fschmid56/efficientat","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"MAX-AST (Single)","metrics":{"Test mAP":"0.481"},"uses_additional_data":false,"paper_date":"2024-04-14","paper":"/paper/max-ast-combining-convolution-local-and","paper_url":"https://cmsworkshops.com/ICASSP2024/view_paper.php?PaperNum=7388","paper_title":"MAX-AST: COMBINING CONVOLUTION, LOCAL AND GLOBAL SELF-ATTENTIONS FOR AUDIO EVENT CLASSIFICATION","code":"https://github.com/ta012/MaxAST","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"ATST-Frame","metrics":{"Test mAP":"0.480"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/self-supervised-audio-teacher-student","paper_url":"https://arxiv.org/abs/2306.04186v2","paper_title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","code":"https://github.com/Audio-WestlakeU/ATST-SED","n_code_links":2,"syntology":null},{"rank_in_archive_order":27,"model":"M2D/0.7","metrics":{"Test mAP":"0.479"},"uses_additional_data":false,"paper_date":"2024-04-09","paper":"/paper/masked-modeling-duo-towards-a-universal-audio","paper_url":"https://arxiv.org/abs/2404.06095v1","paper_title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","code":"https://github.com/nttcslab/m2d","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":28,"model":"PlayItBackX3","metrics":{"Test mAP":"0.477"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/play-it-back-iterative-attention-for-audio","paper_url":"https://arxiv.org/abs/2210.11328v2","paper_title":"Play It Back: Iterative Attention for Audio Recognition","code":"https://github.com/alexandrosstergiou/PlayItBack","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"DASS-Medium (Audio-only, single)","metrics":{"Test mAP":"0.476"},"uses_additional_data":false,"paper_date":"2024-07-04","paper":"/paper/dass-distilled-audio-state-space-models-are","paper_url":"https://arxiv.org/abs/2407.04082v2","paper_title":"DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable Learners","code":"https://github.com/Saurabhbhati/DASS","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":30,"model":"PSLA (Ensemble)","metrics":{"AUC":"0.981","Test mAP":"0.474","d-prime":"2.936"},"uses_additional_data":true,"paper_date":"2021-02-02","paper":"/paper/psla-improving-audio-event-classification","paper_url":"https://arxiv.org/abs/2102.01243v3","paper_title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","code":"https://github.com/YuanGongND/psla","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"DASS-Small (Audio-only, single)","metrics":{"Test mAP":"0.472"},"uses_additional_data":false,"paper_date":"2024-07-04","paper":"/paper/dass-distilled-audio-state-space-models-are","paper_url":"https://arxiv.org/abs/2407.04082v2","paper_title":"DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable Learners","code":"https://github.com/Saurabhbhati/DASS","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":32,"model":"PaSST-S (Single)","metrics":{"Test mAP":"0.471"},"uses_additional_data":true,"paper_date":"2021-10-11","paper":"/paper/efficient-training-of-audio-transformers-with","paper_url":"https://arxiv.org/abs/2110.05069v3","paper_title":"Efficient Training of Audio Transformers with Patchout","code":"https://github.com/kkoutini/passt","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"MaskSpec (AS-2M)","metrics":{"Test mAP":"0.471"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"CAV-MAE (Audio-Only)","metrics":{"Test mAP":"0.466"},"uses_additional_data":true,"paper_date":"2022-10-02","paper":"/paper/contrastive-audio-visual-masked-autoencoder","paper_url":"https://arxiv.org/abs/2210.07839v4","paper_title":"Contrastive Audio-Visual Masked Autoencoder","code":"https://github.com/yuangongnd/cav-mae","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"Audiovisual Masked Autoencoder (Audio-only, Single)","metrics":{"Test mAP":"0.466"},"uses_additional_data":false,"paper_date":"2022-12-09","paper":"/paper/audiovisual-masked-autoencoders","paper_url":"https://arxiv.org/abs/2212.05922v3","paper_title":"Audiovisual Masked Autoencoders","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/av_mae","n_code_links":2,"syntology":null},{"rank_in_archive_order":36,"model":"AudioVisual Fusion Net","metrics":{"AUC":"0.975","Test mAP":"0.462"},"uses_additional_data":false,"paper_date":"2020-05-29","paper":"/paper/large-scale-audiovisual-learning-of-sounds","paper_url":"https://arxiv.org/abs/2006.01595v1","paper_title":"Large Scale Audiovisual Learning of Sounds with Weakly Labeled Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":37,"model":"AST (Single)","metrics":{"Test mAP":"0.459"},"uses_additional_data":true,"paper_date":"2021-04-05","paper":"/paper/ast-audio-spectrogram-transformer","paper_url":"https://arxiv.org/abs/2104.01778v3","paper_title":"AST: Audio Spectrogram Transformer","code":"https://github.com/YuanGongND/ast","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"ERANN-1-6","metrics":{"AUC":"0.976","Test mAP":"0.450","d-prime":"2.804"},"uses_additional_data":false,"paper_date":"2021-06-03","paper":null,"paper_url":"https://arxiv.org/abs/2106.01621v7","paper_title":"ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":39,"model":"Perceiver","metrics":{"Test mAP":"0.449"},"uses_additional_data":false,"paper_date":"2021-03-04","paper":"/paper/perceiver-general-perception-with-iterative","paper_url":"https://arxiv.org/abs/2103.03206v2","paper_title":"Perceiver: General Perception with Iterative Attention","code":"https://github.com/deepmind/deepmind-research/tree/master/perceiver","n_code_links":12,"syntology":{"n_ran":41,"n_unverified":14,"n_samples":55,"n_pointer_only_licence":11}},{"rank_in_archive_order":40,"model":"PSLA (Single)","metrics":{"AUC":"0.975","Test mAP":"0.443","d-prime":"2.778"},"uses_additional_data":true,"paper_date":"2021-02-02","paper":"/paper/psla-improving-audio-event-classification","paper_url":"https://arxiv.org/abs/2102.01243v3","paper_title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","code":"https://github.com/YuanGongND/psla","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"PANNs-CNN14 (Single)","metrics":{"AUC":"0.973","Test mAP":"0.431","d-prime":"2.732"},"uses_additional_data":false,"paper_date":"2020-08-23","paper":"/paper/panns-large-scale-pretrained-audio-neural-1","paper_url":"http://arxiv.org/abs/1912.10211v5","paper_title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","code":"https://github.com/PaddlePaddle/PaddleSpeech","n_code_links":8,"syntology":{"n_ran":2,"n_unverified":14,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"EAT-M","metrics":{"Test mAP":"0.426"},"uses_additional_data":false,"paper_date":"2022-04-25","paper":"/paper/end-to-end-audio-strikes-back-boosting","paper_url":"https://arxiv.org/abs/2204.11479v5","paper_title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","code":"https://github.com/Alibaba-MIIL/AudioClassfication","n_code_links":1,"syntology":null},{"rank_in_archive_order":43,"model":"Conformer (AS-2M)","metrics":{"Test mAP":"0.411"},"uses_additional_data":false,"paper_date":"2021-10-14","paper":"/paper/conformer-based-self-supervised-learning-for","paper_url":"https://arxiv.org/abs/2110.07313v3","paper_title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":44,"model":"EAT-S","metrics":{"Test mAP":"0.405"},"uses_additional_data":false,"paper_date":"2022-04-25","paper":"/paper/end-to-end-audio-strikes-back-boosting","paper_url":"https://arxiv.org/abs/2204.11479v5","paper_title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","code":"https://github.com/Alibaba-MIIL/AudioClassfication","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"WEANet-SUSTAIN","metrics":{"AUC":"0.972","Test mAP":"0.398"},"uses_additional_data":false,"paper_date":"2020-06-30","paper":"/paper/a-sequential-self-teaching-approach-for","paper_url":"https://arxiv.org/abs/2007.00144v1","paper_title":"A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":46,"model":"VATT-Base","metrics":{"AUC":"0.971","Test mAP":"0.394","d-prime":"2.895"},"uses_additional_data":true,"paper_date":"2021-04-22","paper":"/paper/vatt-transformers-for-multimodal-self","paper_url":"https://arxiv.org/abs/2104.11178v3","paper_title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","code":"https://github.com/google-research/google-research/tree/master/vatt","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":47,"model":"Multi-Format Contrastive","metrics":{"Test mAP":"0.376"},"uses_additional_data":false,"paper_date":"2021-03-11","paper":"/paper/multi-format-contrastive-learning-of-audio","paper_url":"https://arxiv.org/abs/2103.06508v3","paper_title":"Multi-Format Contrastive Learning of Audio Representations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":48,"model":"MMV","metrics":{"Test mAP":"0.309"},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/self-supervised-multimodal-versatile-networks","paper_url":"https://arxiv.org/abs/2006.16228v2","paper_title":"Self-Supervised MultiModal Versatile Networks","code":"https://github.com/deepmind/deepmind-research/tree/master/mmv","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"CAV-MAE (Visual-Only)","metrics":{"Test mAP":"0.262"},"uses_additional_data":true,"paper_date":"2022-10-02","paper":"/paper/contrastive-audio-visual-masked-autoencoder","paper_url":"https://arxiv.org/abs/2210.07839v4","paper_title":"Contrastive Audio-Visual Masked Autoencoder","code":"https://github.com/yuangongnd/cav-mae","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"L3","metrics":{"Test mAP":"0.249"},"uses_additional_data":false,"paper_date":"2017-05-23","paper":"/paper/look-listen-and-learn","paper_url":"http://arxiv.org/abs/1705.08168v2","paper_title":"Look, Listen and Learn","code":"https://github.com/marl/l3embedding","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"Triplet","metrics":{"Test mAP":"0.244"},"uses_additional_data":false,"paper_date":"2017-11-06","paper":"/paper/unsupervised-learning-of-semantic-audio","paper_url":"http://arxiv.org/abs/1711.02209v1","paper_title":"Unsupervised Learning of Semantic Audio Representations","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":23,"rows_with_any_sample_ran":18,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":13,"samples_over_distinct_papers":{"n_ran":97,"n_unverified":77,"n_samples":174,"n_pointer_only_licence":27,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":112,"n_unverified":98,"n_samples":210,"n_pointer_only_licence":35,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}