{"task":"Audio Classification","dataset":"FSD50K","metric_names":["mAP","Mean AP"],"rows":[{"id":41268,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"ONE-PEACE","metrics":{"mAP":"69.7"},"paper_url":"https://arxiv.org/abs/2305.11172v1","paper_title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","paper_date":"2023-05-18","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"OFA-Sys/ONE-PEACE","url":"https://github.com/OFA-Sys/ONE-PEACE"}],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":41269,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"MN","metrics":{"mAP":"65.6"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":41270,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"PaSST-S","metrics":{"mAP":"65.55"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":41271,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"DyMN-L","metrics":{"mAP":"65.5"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":41272,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"PaSST-N-S","metrics":{"mAP":"64.2"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":41273,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"PSLA","metrics":{"mAP":"56.71"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":41274,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"MATPAC (SSL Model)","metrics":{"mAP":"55.2"},"paper_url":"https://arxiv.org/abs/2502.12031v1","paper_title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","paper_date":"2025-02-17","code_links":[{"title":"aurianworld/matpac","url":"https://github.com/aurianworld/matpac"}],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":41275,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"Temporal Knowledge Distillation for On-device Audio Classification","metrics":{"mAP":"54.8"},"paper_url":"https://arxiv.org/abs/2110.14131v2","paper_title":"Temporal Knowledge Distillation for On-device Audio Classification","paper_date":"2021-10-27","code_links":[],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":41276,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"Large 6-Layer Transformer with Pooling","metrics":{"mAP":"53.7"},"paper_url":"https://arxiv.org/abs/2105.00335v2","paper_title":"Audio Transformers","paper_date":"2021-05-01","code_links":[],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":41277,"task":"Audio Classification","parent_task":null,"dataset":"FSD50K","model_name":"LHGNN","metrics":{"Mean AP":"59"},"paper_url":"https://arxiv.org/abs/2501.03464v2","paper_title":"LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging","paper_date":"2025-01-07","code_links":[],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122911,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"ONE-PEACE","metrics":{"mAP":"69.7"},"paper_url":"https://arxiv.org/abs/2305.11172v1","paper_title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","paper_date":"2023-05-18","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"OFA-Sys/ONE-PEACE","url":"https://github.com/OFA-Sys/ONE-PEACE"}],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":122912,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"MN","metrics":{"mAP":"65.6"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":122913,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"PaSST-S","metrics":{"mAP":"65.55"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":122914,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"DyMN-L","metrics":{"mAP":"65.5"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":122915,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"PaSST-N-S","metrics":{"mAP":"64.2"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":122916,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"PSLA","metrics":{"mAP":"56.71"},"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":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":122917,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"MATPAC (SSL Model)","metrics":{"mAP":"55.2"},"paper_url":"https://arxiv.org/abs/2502.12031v1","paper_title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","paper_date":"2025-02-17","code_links":[{"title":"aurianworld/matpac","url":"https://github.com/aurianworld/matpac"}],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122918,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"Temporal Knowledge Distillation for On-device Audio Classification","metrics":{"mAP":"54.8"},"paper_url":"https://arxiv.org/abs/2110.14131v2","paper_title":"Temporal Knowledge Distillation for On-device Audio Classification","paper_date":"2021-10-27","code_links":[],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122919,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"Large 6-Layer Transformer with Pooling","metrics":{"mAP":"53.7"},"paper_url":"https://arxiv.org/abs/2105.00335v2","paper_title":"Audio Transformers","paper_date":"2021-05-01","code_links":[],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122920,"task":"Audio Classification","parent_task":"Classification","dataset":"FSD50K","model_name":"LHGNN","metrics":{"Mean AP":"59"},"paper_url":"https://arxiv.org/abs/2501.03464v2","paper_title":"LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging","paper_date":"2025-01-07","code_links":[],"metrics_order":"[\"mAP\", \"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]}]}