{"task":"Object Counting","dataset":"TallyQA-Simple","metric_names":["Accuracy","RMSE"],"rows":[{"id":52822,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Simple","model_name":"SMoLA-PaLI-X Specialist","metrics":{"Accuracy":"86.3"},"paper_url":"https://arxiv.org/abs/2312.00968v2","paper_title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","paper_date":"2023-12-01","code_links":[],"metrics_order":"[\"Accuracy\", \"RMSE\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":52823,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Simple","model_name":"PaLI-X-VPD","metrics":{"Accuracy":"86.2"},"paper_url":"https://arxiv.org/abs/2312.03052v2","paper_title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","paper_date":"2023-12-05","code_links":[],"metrics_order":"[\"Accuracy\", \"RMSE\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52824,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Simple","model_name":"SMoLA-PaLI-X Generalist (0 shot)","metrics":{"Accuracy":"83.3"},"paper_url":"https://arxiv.org/abs/2312.00968v2","paper_title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","paper_date":"2023-12-01","code_links":[],"metrics_order":"[\"Accuracy\", \"RMSE\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":52825,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Simple","model_name":"MoVie-ResNeXt","metrics":{"Accuracy":"74.9","RMSE":"1"},"paper_url":"https://arxiv.org/abs/2004.11883v3","paper_title":"MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond","paper_date":"2020-04-24","code_links":[{"title":"facebookresearch/mmf","url":"https://github.com/facebookresearch/mmf/tree/master/projects/movie_mcan"}],"metrics_order":"[\"Accuracy\", \"RMSE\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52826,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Simple","model_name":"RCN","metrics":{"Accuracy":"71.8","RMSE":"1.13"},"paper_url":"http://arxiv.org/abs/1810.12440v2","paper_title":"TallyQA: Answering Complex Counting Questions","paper_date":"2018-10-29","code_links":[{"title":"manoja328/tallyqacode","url":"https://github.com/manoja328/tallyqacode"}],"metrics_order":"[\"Accuracy\", \"RMSE\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52827,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Simple","model_name":"MoVie","metrics":{"Accuracy":"70.8","RMSE":"1.09"},"paper_url":"https://arxiv.org/abs/2004.11883v3","paper_title":"MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond","paper_date":"2020-04-24","code_links":[{"title":"facebookresearch/mmf","url":"https://github.com/facebookresearch/mmf/tree/master/projects/movie_mcan"}],"metrics_order":"[\"Accuracy\", \"RMSE\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}