{"task":"Audio Classification","dataset":"Audio Set","metric_names":["Mean AP"],"rows":[{"id":41235,"task":"Audio Classification","parent_task":null,"dataset":"Audio Set","model_name":"M2D-AS/0.7","metrics":{"Mean AP":"48.5"},"paper_url":"https://arxiv.org/abs/2404.06095v1","paper_title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","paper_date":"2024-04-09","code_links":[{"title":"nttcslab/m2d","url":"https://github.com/nttcslab/m2d"},{"title":"nttcslab/eval-audio-repr","url":"https://github.com/nttcslab/eval-audio-repr"}],"metrics_order":"[\"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":41236,"task":"Audio Classification","parent_task":null,"dataset":"Audio Set","model_name":"LHGNN","metrics":{"Mean AP":"46.6"},"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":"[\"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":41237,"task":"Audio Classification","parent_task":null,"dataset":"Audio Set","model_name":"VAB-Encodec (Ours)","metrics":{"Mean AP":"38.7"},"paper_url":"https://arxiv.org/abs/2409.19132v1","paper_title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","paper_date":"2024-09-27","code_links":[{"title":"DragonLiu1995/Vision-to-Audio-and-Beyond","url":"https://github.com/DragonLiu1995/Vision-to-Audio-and-Beyond"}],"metrics_order":"[\"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122878,"task":"Audio Classification","parent_task":"Classification","dataset":"Audio Set","model_name":"M2D-AS/0.7","metrics":{"Mean AP":"48.5"},"paper_url":"https://arxiv.org/abs/2404.06095v1","paper_title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","paper_date":"2024-04-09","code_links":[{"title":"nttcslab/m2d","url":"https://github.com/nttcslab/m2d"},{"title":"nttcslab/eval-audio-repr","url":"https://github.com/nttcslab/eval-audio-repr"}],"metrics_order":"[\"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122879,"task":"Audio Classification","parent_task":"Classification","dataset":"Audio Set","model_name":"LHGNN","metrics":{"Mean AP":"46.6"},"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":"[\"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122880,"task":"Audio Classification","parent_task":"Classification","dataset":"Audio Set","model_name":"VAB-Encodec (Ours)","metrics":{"Mean AP":"38.7"},"paper_url":"https://arxiv.org/abs/2409.19132v1","paper_title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","paper_date":"2024-09-27","code_links":[{"title":"DragonLiu1995/Vision-to-Audio-and-Beyond","url":"https://github.com/DragonLiu1995/Vision-to-Audio-and-Beyond"}],"metrics_order":"[\"Mean AP\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]}]}