{"task":"Action Classification","dataset":"AViD","metric_names":["Accuracy"],"rows":[{"id":17798,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"TokenLearner","metrics":{"Accuracy":"53.8"},"paper_url":"https://arxiv.org/abs/2106.11297v4","paper_title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","paper_date":"2021-06-21","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"},{"title":"keras-team/keras-io","url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/token_learner.py"},{"title":"rish-16/tokenlearner-pytorch","url":"https://github.com/rish-16/tokenlearner-pytorch"},{"title":"ariG23498/TokenLearner","url":"https://github.com/ariG23498/TokenLearner"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/7/token_learner"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/4/token_learner"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/token_learner"},{"title":"MindSpore-scientific/code-1","url":"https://github.com/MindSpore-scientific/code-1/tree/main/token_learner"},{"title":"MindSpore-scientific/code-8","url":"https://github.com/MindSpore-scientific/code-8/tree/main/token_learner"},{"title":"MindSpore-scientific/code-10","url":"https://github.com/MindSpore-scientific/code-10/tree/main/token_learner"},{"title":"MindSpore-scientific-2/code-8","url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/token_learner"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":17799,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"SlowFast-101 16x8","metrics":{"Accuracy":"50.9"},"paper_url":"https://arxiv.org/abs/2007.05515v3","paper_title":"AViD Dataset: Anonymized Videos from Diverse Countries","paper_date":"2020-07-10","code_links":[{"title":"piergiaj/AViD","url":"https://github.com/piergiaj/AViD"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":17800,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"RepFlow ResNet-50","metrics":{"Accuracy":"50.5"},"paper_url":"https://arxiv.org/abs/2007.05515v3","paper_title":"AViD Dataset: Anonymized Videos from Diverse Countries","paper_date":"2020-07-10","code_links":[{"title":"piergiaj/AViD","url":"https://github.com/piergiaj/AViD"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":17801,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"SlowFast-50 8x8","metrics":{"Accuracy":"50.4"},"paper_url":"https://arxiv.org/abs/2007.05515v3","paper_title":"AViD Dataset: Anonymized Videos from Diverse Countries","paper_date":"2020-07-10","code_links":[{"title":"piergiaj/AViD","url":"https://github.com/piergiaj/AViD"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":17802,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"Two-Stream 3D ResNet-50","metrics":{"Accuracy":"50.1"},"paper_url":"https://arxiv.org/abs/2007.05515v3","paper_title":"AViD Dataset: Anonymized Videos from Diverse Countries","paper_date":"2020-07-10","code_links":[{"title":"piergiaj/AViD","url":"https://github.com/piergiaj/AViD"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":17803,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"(2+1)D ResNet-50","metrics":{"Accuracy":"48.8"},"paper_url":"https://arxiv.org/abs/2007.05515v3","paper_title":"AViD Dataset: Anonymized Videos from Diverse Countries","paper_date":"2020-07-10","code_links":[{"title":"piergiaj/AViD","url":"https://github.com/piergiaj/AViD"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":17804,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"SlowFast-50 4x4","metrics":{"Accuracy":"48.5"},"paper_url":"https://arxiv.org/abs/2007.05515v3","paper_title":"AViD Dataset: Anonymized Videos from Diverse Countries","paper_date":"2020-07-10","code_links":[{"title":"piergiaj/AViD","url":"https://github.com/piergiaj/AViD"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":17805,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"3D ResNet-50","metrics":{"Accuracy":"48.2"},"paper_url":"https://arxiv.org/abs/2007.05515v3","paper_title":"AViD Dataset: Anonymized Videos from Diverse Countries","paper_date":"2020-07-10","code_links":[{"title":"piergiaj/AViD","url":"https://github.com/piergiaj/AViD"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":17806,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"I3D","metrics":{"Accuracy":"46.8"},"paper_url":"https://arxiv.org/abs/2007.05515v3","paper_title":"AViD Dataset: Anonymized Videos from Diverse Countries","paper_date":"2020-07-10","code_links":[{"title":"piergiaj/AViD","url":"https://github.com/piergiaj/AViD"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":17807,"task":"Action Classification","parent_task":"Video","dataset":"AViD","model_name":"2D ResNet-50","metrics":{"Accuracy":"36.2"},"paper_url":"https://arxiv.org/abs/2007.05515v3","paper_title":"AViD Dataset: Anonymized Videos from Diverse Countries","paper_date":"2020-07-10","code_links":[{"title":"piergiaj/AViD","url":"https://github.com/piergiaj/AViD"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}