{"task":"Audio Classification","dataset":"DCASE","metric_names":["Top-1 Accuracy","PRE-TRAINING DATASET"],"rows":[{"id":41241,"task":"Audio Classification","parent_task":null,"dataset":"DCASE","model_name":"CrissCross (AudioSet)","metrics":{"PRE-TRAINING DATASET":"AudioSet","Top-1 Accuracy":"97"},"paper_url":"https://arxiv.org/abs/2111.05329v5","paper_title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","paper_date":"2021-11-09","code_links":[{"title":"pritamqu/CrissCross","url":"https://github.com/pritamqu/CrissCross"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":41242,"task":"Audio Classification","parent_task":null,"dataset":"DCASE","model_name":"CrissCross (Kinetics-400)","metrics":{"PRE-TRAINING DATASET":"Kinetics-400","Top-1 Accuracy":"96"},"paper_url":"https://arxiv.org/abs/2111.05329v5","paper_title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","paper_date":"2021-11-09","code_links":[{"title":"pritamqu/CrissCross","url":"https://github.com/pritamqu/CrissCross"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":41243,"task":"Audio Classification","parent_task":null,"dataset":"DCASE","model_name":"XDC","metrics":{"PRE-TRAINING DATASET":"IG-Random","Top-1 Accuracy":"95"},"paper_url":"https://arxiv.org/abs/1911.12667v3","paper_title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","paper_date":"2019-11-28","code_links":[{"title":"HumamAlwassel/XDC","url":"https://github.com/HumamAlwassel/XDC"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":41244,"task":"Audio Classification","parent_task":null,"dataset":"DCASE","model_name":"XDC","metrics":{"PRE-TRAINING DATASET":"AudioSet","Top-1 Accuracy":"95"},"paper_url":"https://arxiv.org/abs/1911.12667v3","paper_title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","paper_date":"2019-11-28","code_links":[{"title":"HumamAlwassel/XDC","url":"https://github.com/HumamAlwassel/XDC"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":41245,"task":"Audio Classification","parent_task":null,"dataset":"DCASE","model_name":"CrissCross (Kinetics-Sound)","metrics":{"PRE-TRAINING DATASET":"Kinetics-Sound","Top-1 Accuracy":"93"},"paper_url":"https://arxiv.org/abs/2111.05329v5","paper_title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","paper_date":"2021-11-09","code_links":[{"title":"pritamqu/CrissCross","url":"https://github.com/pritamqu/CrissCross"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122884,"task":"Audio Classification","parent_task":"Classification","dataset":"DCASE","model_name":"CrissCross (AudioSet)","metrics":{"PRE-TRAINING DATASET":"AudioSet","Top-1 Accuracy":"97"},"paper_url":"https://arxiv.org/abs/2111.05329v5","paper_title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","paper_date":"2021-11-09","code_links":[{"title":"pritamqu/CrissCross","url":"https://github.com/pritamqu/CrissCross"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122885,"task":"Audio Classification","parent_task":"Classification","dataset":"DCASE","model_name":"CrissCross (Kinetics-400)","metrics":{"PRE-TRAINING DATASET":"Kinetics-400","Top-1 Accuracy":"96"},"paper_url":"https://arxiv.org/abs/2111.05329v5","paper_title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","paper_date":"2021-11-09","code_links":[{"title":"pritamqu/CrissCross","url":"https://github.com/pritamqu/CrissCross"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122886,"task":"Audio Classification","parent_task":"Classification","dataset":"DCASE","model_name":"XDC","metrics":{"PRE-TRAINING DATASET":"IG-Random","Top-1 Accuracy":"95"},"paper_url":"https://arxiv.org/abs/1911.12667v3","paper_title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","paper_date":"2019-11-28","code_links":[{"title":"HumamAlwassel/XDC","url":"https://github.com/HumamAlwassel/XDC"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122887,"task":"Audio Classification","parent_task":"Classification","dataset":"DCASE","model_name":"XDC","metrics":{"PRE-TRAINING DATASET":"AudioSet","Top-1 Accuracy":"95"},"paper_url":"https://arxiv.org/abs/1911.12667v3","paper_title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","paper_date":"2019-11-28","code_links":[{"title":"HumamAlwassel/XDC","url":"https://github.com/HumamAlwassel/XDC"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":122888,"task":"Audio Classification","parent_task":"Classification","dataset":"DCASE","model_name":"CrissCross (Kinetics-Sound)","metrics":{"PRE-TRAINING DATASET":"Kinetics-Sound","Top-1 Accuracy":"93"},"paper_url":"https://arxiv.org/abs/2111.05329v5","paper_title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","paper_date":"2021-11-09","code_links":[{"title":"pritamqu/CrissCross","url":"https://github.com/pritamqu/CrissCross"}],"metrics_order":"[\"Top-1 Accuracy\", \"PRE-TRAINING DATASET\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]}]}