{"task":"Object Counting","dataset":"TallyQA-Complex","metric_names":["Accuracy","RMSE"],"rows":[{"id":52815,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Complex","model_name":"SMoLA-PaLI-X Specialist","metrics":{"Accuracy":"77.1"},"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":52816,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Complex","model_name":"PaLI-X-VPD","metrics":{"Accuracy":"76.6"},"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":52817,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Complex","model_name":"SMoLA-PaLI-X Generalist (0 shot)","metrics":{"Accuracy":"70.7"},"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":52818,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Complex","model_name":"MoVie-ResNeXt","metrics":{"Accuracy":"56.8","RMSE":"1.43"},"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":52819,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Complex","model_name":"RCN","metrics":{"Accuracy":"56.2","RMSE":"1.43"},"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":52820,"task":"Object Counting","parent_task":null,"dataset":"TallyQA-Complex","model_name":"MoVie","metrics":{"Accuracy":"54.1","RMSE":"1.52"},"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":[]}]}