{"url":"/sota/object-counting-on-tallyqa-complex","task":{"name":"Object Counting","url":"/task/object-counting","note":null},"dataset":{"name":"TallyQA-Complex","url":"/dataset/tallyqa"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The goal of **Object Counting** task is to count the number of object instances in a single image or video sequence. It has many real-world applications such as traffic flow monitoring, crowdedness estimation, and product counting.\n\n\n<span class=\"description-source\">Source: [Learning to Count Objects with Few Exemplar Annotations ](https://arxiv.org/abs/1905.07898)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy","RMSE"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","RMSE":"lower"}},"counts":{"rows":6,"rows_with_code":3,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"SMoLA-PaLI-X Specialist","metrics":{"Accuracy":"77.1"},"uses_additional_data":true,"paper_date":"2023-12-01","paper":"/paper/omni-smola-boosting-generalist-multimodal","paper_url":"https://arxiv.org/abs/2312.00968v2","paper_title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"PaLI-X-VPD","metrics":{"Accuracy":"76.6"},"uses_additional_data":false,"paper_date":"2023-12-05","paper":"/paper/visual-program-distillation-distilling-tools","paper_url":"https://arxiv.org/abs/2312.03052v2","paper_title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"SMoLA-PaLI-X Generalist (0 shot)","metrics":{"Accuracy":"70.7"},"uses_additional_data":true,"paper_date":"2023-12-01","paper":"/paper/omni-smola-boosting-generalist-multimodal","paper_url":"https://arxiv.org/abs/2312.00968v2","paper_title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"MoVie-ResNeXt","metrics":{"Accuracy":"56.8","RMSE":"1.43"},"uses_additional_data":false,"paper_date":"2020-04-24","paper":"/paper/revisiting-modulated-convolutions-for-visual","paper_url":"https://arxiv.org/abs/2004.11883v3","paper_title":"MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond","code":"https://github.com/facebookresearch/mmf/tree/master/projects/movie_mcan","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"RCN","metrics":{"Accuracy":"56.2","RMSE":"1.43"},"uses_additional_data":false,"paper_date":"2018-10-29","paper":"/paper/tallyqa-answering-complex-counting-questions","paper_url":"http://arxiv.org/abs/1810.12440v2","paper_title":"TallyQA: Answering Complex Counting Questions","code":"https://github.com/manoja328/tallyqacode","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"MoVie","metrics":{"Accuracy":"54.1","RMSE":"1.52"},"uses_additional_data":false,"paper_date":"2020-04-24","paper":"/paper/revisiting-modulated-convolutions-for-visual","paper_url":"https://arxiv.org/abs/2004.11883v3","paper_title":"MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond","code":"https://github.com/facebookresearch/mmf/tree/master/projects/movie_mcan","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}