{"task":"Audio Tagging","dataset":"AudioSet","metric_names":["mean average precision"],"rows":[{"id":46805,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"CAV-MAE (Audio-Visual)","metrics":{"mean average precision":"0.512"},"paper_url":"https://arxiv.org/abs/2210.07839v4","paper_title":"Contrastive Audio-Visual Masked Autoencoder","paper_date":"2022-10-02","code_links":[{"title":"yuangongnd/cav-mae","url":"https://github.com/yuangongnd/cav-mae"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":46806,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"mn40_as (Ensemble)","metrics":{"mean average precision":"0.498"},"paper_url":"https://arxiv.org/abs/2211.04772v3","paper_title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","paper_date":"2022-11-09","code_links":[{"title":"fschmid56/efficientat","url":"https://github.com/fschmid56/efficientat"},{"title":"fschmid56/efficientat_hear","url":"https://github.com/fschmid56/efficientat_hear"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":46807,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"PaSST","metrics":{"mean average precision":"0.496"},"paper_url":"https://arxiv.org/abs/2110.05069v3","paper_title":"Efficient Training of Audio Transformers with Patchout","paper_date":"2021-10-11","code_links":[{"title":"kkoutini/passt","url":"https://github.com/kkoutini/passt"},{"title":"kkoutini/passt_hear21","url":"https://github.com/kkoutini/passt_hear21"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":46808,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"DyMN-L (Audio-Only, Single)","metrics":{"mean average precision":"0.490"},"paper_url":"https://arxiv.org/abs/2310.15648v1","paper_title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","paper_date":"2023-10-24","code_links":[{"title":"fschmid56/efficientat","url":"https://github.com/fschmid56/efficientat"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":46809,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"Audio Spectrogram Transformer","metrics":{"mean average precision":"0.485"},"paper_url":"https://arxiv.org/abs/2104.01778v3","paper_title":"AST: Audio Spectrogram Transformer","paper_date":"2021-04-05","code_links":[{"title":"YuanGongND/ast","url":"https://github.com/YuanGongND/ast"},{"title":"nttcslab/composing-general-audio-repr","url":"https://github.com/nttcslab/composing-general-audio-repr"},{"title":"pxaris/ccml","url":"https://github.com/pxaris/ccml"},{"title":"cgaroufis/msspt","url":"https://github.com/cgaroufis/msspt"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/audio_spectrogram_transformer"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":46810,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"mn40_as (Single)","metrics":{"mean average precision":"0.483"},"paper_url":"https://arxiv.org/abs/2211.04772v3","paper_title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","paper_date":"2022-11-09","code_links":[{"title":"fschmid56/efficientat","url":"https://github.com/fschmid56/efficientat"},{"title":"fschmid56/efficientat_hear","url":"https://github.com/fschmid56/efficientat_hear"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":46811,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"PSLA","metrics":{"mean average precision":"0.474"},"paper_url":"https://arxiv.org/abs/2102.01243v3","paper_title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","paper_date":"2021-02-02","code_links":[{"title":"YuanGongND/psla","url":"https://github.com/YuanGongND/psla"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":46812,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"ST-SED","metrics":{"mean average precision":"0.467"},"paper_url":"https://arxiv.org/abs/2112.07891v4","paper_title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","paper_date":"2021-12-15","code_links":[{"title":"RetroCirce/Zero_Shot_Audio_Source_Separation","url":"https://github.com/RetroCirce/Zero_Shot_Audio_Source_Separation"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":46813,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"CAV-MAE (Audio-Only)","metrics":{"mean average precision":"0.466"},"paper_url":"https://arxiv.org/abs/2210.07839v4","paper_title":"Contrastive Audio-Visual Masked Autoencoder","paper_date":"2022-10-02","code_links":[{"title":"yuangongnd/cav-mae","url":"https://github.com/yuangongnd/cav-mae"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":46814,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"ERANN-1-6","metrics":{"mean average precision":"0.450"},"paper_url":"https://arxiv.org/abs/2106.01621v7","paper_title":"ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition","paper_date":"2021-06-03","code_links":[],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":46815,"task":"Audio Tagging","parent_task":null,"dataset":"AudioSet","model_name":"CNN14","metrics":{"mean average precision":"0.431"},"paper_url":"http://arxiv.org/abs/1912.10211v5","paper_title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","paper_date":"2020-08-23","code_links":[{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"qiuqiangkong/audioset_tagging_cnn","url":"https://github.com/qiuqiangkong/audioset_tagging_cnn"},{"title":"google-research/leaf-audio","url":"https://github.com/google-research/leaf-audio"},{"title":"gudgud96/frechet-audio-distance","url":"https://github.com/gudgud96/frechet-audio-distance"},{"title":"yinkalario/General-Purpose-Sound-Recognition-Demo","url":"https://github.com/yinkalario/General-Purpose-Sound-Recognition-Demo"},{"title":"YuanGongND/psla","url":"https://github.com/YuanGongND/psla"},{"title":"nttcslab/composing-general-audio-repr","url":"https://github.com/nttcslab/composing-general-audio-repr"},{"title":"sithu31296/audio-tagging","url":"https://github.com/sithu31296/audio-tagging"}],"metrics_order":"[\"mean average precision\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]}]}