{"task":"Action Classification","dataset":"ActivityNet","metric_names":["Top 1 Accuracy","Top 5 Accuracy"],"rows":[{"id":17810,"task":"Action Classification","parent_task":"Video","dataset":"ActivityNet","model_name":"UniFormerV2-L","metrics":{"Top 1 Accuracy":"94.7","Top 5 Accuracy":"99.5"},"paper_url":"https://openreview.net/forum?id=d77RVuVg-Mf","paper_title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","paper_date":"2022-09-22","code_links":[{"title":"OpenGVLab/UniFormerV2","url":"https://github.com/OpenGVLab/UniFormerV2"},{"title":"innat/UniFormerV2","url":"https://github.com/innat/UniFormerV2"}],"metrics_order":"[\"Top 1 Accuracy\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]}]}