{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/object-counting","name":"Object Counting","slug":"object-counting","description_markdown":"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>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":158,"papers_with_code":81,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":28,"subtasks":4,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/object-counting-on-fsc147","slug":"object-counting-on-fsc147","dataset":"FSC147","dataset_url":"/dataset/fsc147","rows_in_archive":19,"metrics":["MAE(test)","MAE(val)","RMSE(test)","RMSE(val)"],"first_row_in_archive_order":{"model":"CountGD","paper_title":"CountGD: Multi-Modal Open-World Counting","paper_url":"/paper/countgd-multi-modal-open-world-counting","paper_date":"2024-07-05","arxiv_id":"2407.04619","code_links":[{"title":"niki-amini-naieni/CountGD","url":"https://github.com/niki-amini-naieni/CountGD"},{"title":"niki-amini-naieni/countx","url":"https://github.com/niki-amini-naieni/countx"}],"syntology":{"n":9,"n_ran":4,"n_constructed":1,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/countgd-multi-modal-open-world-counting#ran","syntology_url":"https://syntology.ai/paper/2407.04619","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04619"}},"official":null}}},{"leaderboard":"/sota/object-counting-on-carpk","slug":"object-counting-on-carpk","dataset":"CARPK","dataset_url":"/dataset/carpk","rows_in_archive":15,"metrics":["MAE","RMSE"],"first_row_in_archive_order":{"model":"HLCNN","paper_title":"An Accurate Car Counting in Aerial Images Based on Convolutional Neural Networks","paper_url":"/paper/an-accurate-car-counting-in-aerial-images","paper_date":"2021-07-13","arxiv_id":null,"code_links":[{"title":"ekilic/Heatmap-Learner-CNN-for-Object-Counting","url":"https://github.com/ekilic/Heatmap-Learner-CNN-for-Object-Counting"}],"syntology":null}},{"leaderboard":"/sota/object-counting-on-pascal-voc-2007-count-test","slug":"object-counting-on-pascal-voc-2007-count-test","dataset":"Pascal VOC 2007 count-test","dataset_url":"/dataset/pascal-voc-2007","rows_in_archive":8,"metrics":["m-reIRMSE-nz","m-relRMSE","mRMSE","mRMSE-nz"],"first_row_in_archive_order":{"model":"Supervised Density Map","paper_title":"Object Counting and Instance Segmentation with Image-level Supervision","paper_url":"/paper/object-counting-and-instance-segmentation","paper_date":"2019-03-06","arxiv_id":"1903.02494","code_links":[{"title":"GuoleiSun/CountSeg","url":"https://github.com/GuoleiSun/CountSeg"},{"title":"alzayats/CountSeg-1","url":"https://github.com/alzayats/CountSeg-1"}],"syntology":null}},{"leaderboard":"/sota/object-counting-on-coco-count-test","slug":"object-counting-on-coco-count-test","dataset":"COCO count-test","dataset_url":"/dataset/coco","rows_in_archive":7,"metrics":["m-reIRMSE","m-reIRMSE-nz","mRMSE","mRMSE-nz"],"first_row_in_archive_order":{"model":"ens","paper_title":"Counting Everyday Objects in Everyday Scenes","paper_url":"/paper/counting-everyday-objects-in-everyday-scenes","paper_date":"2016-04-12","arxiv_id":"1604.03505","code_links":[{"title":"prithv1/cvpr2017_counting","url":"https://github.com/prithv1/cvpr2017_counting"}],"syntology":null}},{"leaderboard":"/sota/object-counting-on-tallyqa-complex","slug":"object-counting-on-tallyqa-complex","dataset":"TallyQA-Complex","dataset_url":"/dataset/tallyqa","rows_in_archive":6,"metrics":["Accuracy","RMSE"],"first_row_in_archive_order":{"model":"SMoLA-PaLI-X Specialist","paper_title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","paper_url":"/paper/omni-smola-boosting-generalist-multimodal","paper_date":"2023-12-01","arxiv_id":"2312.00968","code_links":[],"syntology":null}},{"leaderboard":"/sota/object-counting-on-tallyqa-simple","slug":"object-counting-on-tallyqa-simple","dataset":"TallyQA-Simple","dataset_url":"/dataset/tallyqa","rows_in_archive":6,"metrics":["Accuracy","RMSE"],"first_row_in_archive_order":{"model":"SMoLA-PaLI-X Specialist","paper_title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","paper_url":"/paper/omni-smola-boosting-generalist-multimodal","paper_date":"2023-12-01","arxiv_id":"2312.00968","code_links":[],"syntology":null}},{"leaderboard":"/sota/object-counting-on-howmany-qa","slug":"object-counting-on-howmany-qa","dataset":"HowMany-QA","dataset_url":"/dataset/howmany-qa","rows_in_archive":3,"metrics":["Accuracy","RMSE"],"first_row_in_archive_order":{"model":"MoVie-ResNeXt","paper_title":"MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond","paper_url":"/paper/revisiting-modulated-convolutions-for-visual","paper_date":"2020-04-24","arxiv_id":"2004.11883","code_links":[{"title":"facebookresearch/mmf","url":"https://github.com/facebookresearch/mmf/tree/master/projects/movie_mcan"}],"syntology":null}},{"leaderboard":"/sota/object-counting-on-pascal-voc","slug":"object-counting-on-pascal-voc","dataset":"PASCAL VOC","dataset_url":"/dataset/pascal-voc","rows_in_archive":3,"metrics":["mRMSE"],"first_row_in_archive_order":{"model":"TFOC","paper_title":"Training-free Object Counting with Prompts","paper_url":"/paper/training-free-object-counting-with-prompts","paper_date":"2023-06-30","arxiv_id":"2307.00038","code_links":[{"title":"shizenglin/training-free-object-counter","url":"https://github.com/shizenglin/training-free-object-counter"}],"syntology":null}},{"leaderboard":"/sota/object-counting-on-omnicount-191","slug":"object-counting-on-omnicount-191","dataset":"Omnicount-191","dataset_url":"/dataset/omnicount-191","rows_in_archive":1,"metrics":["mRMSE"],"first_row_in_archive_order":{"model":"Omnicount","paper_title":"OmniCount: Multi-label Object Counting with Semantic-Geometric Priors","paper_url":"/paper/omnicount-multi-label-object-counting-with","paper_date":"2024-03-08","arxiv_id":"2403.05435","code_links":[],"syntology":null}},{"leaderboard":"/sota/object-counting-on-trancos","slug":"object-counting-on-trancos","dataset":"TRANCOS","dataset_url":"/dataset/trancos","rows_in_archive":1,"metrics":["MAE","MSE"],"first_row_in_archive_order":{"model":"GauNet (ResNet-50)","paper_title":"Rethinking Spatial Invariance of Convolutional Networks for Object Counting","paper_url":"/paper/rethinking-spatial-invariance-of-1","paper_date":"2022-06-10","arxiv_id":"2206.05253","code_links":[{"title":"zhiqic/rethinking-counting","url":"https://github.com/zhiqic/rethinking-counting"}],"syntology":null}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/pascal-voc","name":"PASCAL VOC","full_name":"PASCAL Visual Object Classes Challenge","num_papers_in_archive":198},{"url":"/dataset/pascal-voc-2007","name":"PASCAL VOC 2007","full_name":"PASCAL VOC 2007","num_papers_in_archive":126},{"url":"/dataset/carpk","name":"CARPK","full_name":"car parking lot dataset","num_papers_in_archive":71},{"url":"/dataset/fsod","name":"FSOD","full_name":"Few-Shot Object Detection Dataset","num_papers_in_archive":68},{"url":"/dataset/fsc147","name":"FSC147","full_name":"","num_papers_in_archive":58},{"url":"/dataset/tallyqa","name":"TallyQA","full_name":"","num_papers_in_archive":33},{"url":"/dataset/cowc","name":"COWC","full_name":"Cars Overhead With Context","num_papers_in_archive":22},{"url":"/dataset/cost","name":"COST","full_name":"COCO Segmentation Text","num_papers_in_archive":11},{"url":"/dataset/agar","name":"AGAR","full_name":"Annotated Germs for Automated Recognition","num_papers_in_archive":7},{"url":"/dataset/trancos","name":"TRANCOS","full_name":"TRaffic ANd COngestionS","num_papers_in_archive":7},{"url":"/dataset/25ktrees","name":"25kTrees","full_name":"Individual Tree Crown Annotations","num_papers_in_archive":5},{"url":"/dataset/howmany-qa","name":"HowMany-QA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/rf100","name":"RF100","full_name":"Roboflow 100","num_papers_in_archive":5},{"url":"/dataset/fluocells","name":"fluocells","full_name":"Fluorescent Neuronal Cells","num_papers_in_archive":3},{"url":"/dataset/iwildcam-2021","name":"iWildCam 2021","full_name":"","num_papers_in_archive":3},{"url":"/dataset/blue-cells-enumeration-dataset","name":"Blue Cells enumeration dataset","full_name":"Learning to Count Objects in Images blue cells dataset","num_papers_in_archive":2},{"url":"/dataset/leukemiaattri","name":"LeukemiaAttri","full_name":"","num_papers_in_archive":2},{"url":"/dataset/rsoc","name":"RSOC","full_name":"Remote Sensing Object Counting","num_papers_in_archive":2},{"url":"/dataset/smartcity","name":"SmartCity","full_name":"","num_papers_in_archive":2},{"url":"/dataset/acct-data-repository","name":"ACCT Data Repository","full_name":"ACCT is a fast and accessible automatic cell counting tool using machine learning for 2D image segmentation","num_papers_in_archive":1},{"url":"/dataset/artificial-fluorescent-bacteria-dataset","name":"Artificial fluorescent bacteria dataset","full_name":"Artificial fluorescent bacteria dataset","num_papers_in_archive":1},{"url":"/dataset/bbbc041","name":"BBBC041","full_name":"P. vivax (malaria) infected human blood smears","num_papers_in_archive":1},{"url":"/dataset/fish-counting","name":"Fish Counting","full_name":"","num_papers_in_archive":1},{"url":"/dataset/locount","name":"Locount","full_name":"","num_papers_in_archive":1},{"url":"/dataset/omnicount-191","name":"Omnicount-191","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vgg-cell","name":"VGG Cell","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/penguin-dataset","name":"Penguin dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/exemplar-free-counting","name":"Exemplar-Free Counting"},{"url":"/task/few-shot-object-counting-and-detection","name":"Few-shot Object Counting and Detection"},{"url":"/task/open-vocabulary-object-counting","name":"Open-vocabulary object counting"},{"url":"/task/training-free-object-counting","name":"Training-free Object Counting"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":158,"of_with_code":81,"tagged_in_all":158,"counts":{"archive_papers_tagged":158,"with_a_code_link":81,"where_syntology_ran_a_sample":24,"not_listed_spam_title":0,"listed":158,"listed_where_code_ran":24,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":21,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":21,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/yolo9000-better-faster-stronger","slug":"yolo9000-better-faster-stronger","title":"YOLO9000: Better, Faster, Stronger","date":"2016-12-25","arxiv_id":"1612.08242","repositories_listed":231,"syntology":{"n":60,"n_ran":44,"n_constructed":0,"n_ran_checked":33,"n_instrument":11,"n_unverified":16,"n_honours":1,"n_violates":4,"n_no_contract":28,"n_pointer_only":23,"phrase":"44 ran (of which 0 constructed an object rather than computing a result; 33 with no instrument failure: 1 honoured, 4 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 16 unverified","sample_list":"/paper/yolo9000-better-faster-stronger#ran","syntology_url":"https://syntology.ai/paper/1612.08242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.08242"}},"official":null}},{"url":"/paper/you-only-look-once-unified-real-time-object","slug":"you-only-look-once-unified-real-time-object","title":"You Only Look Once: Unified, Real-Time Object Detection","date":"2015-06-08","arxiv_id":"1506.02640","repositories_listed":144,"syntology":{"n":148,"n_ran":89,"n_constructed":27,"n_ran_checked":58,"n_instrument":31,"n_unverified":59,"n_honours":4,"n_violates":4,"n_no_contract":50,"n_pointer_only":98,"phrase":"89 ran (of which 27 constructed an object rather than computing a result; 58 with no instrument failure: 4 honoured, 4 violated, 50 with no contract checked; 31 where Syntology's instrument failed) · 59 unverified","sample_list":"/paper/you-only-look-once-unified-real-time-object#ran","syntology_url":"https://syntology.ai/paper/1506.02640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.02640"}},"official":null}},{"url":"/paper/self-supervised-learning-from-images-with-a","slug":"self-supervised-learning-from-images-with-a","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","date":"2023-01-19","arxiv_id":"2301.08243","repositories_listed":7,"syntology":{"n":14,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":13,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/self-supervised-learning-from-images-with-a#ran","syntology_url":"https://syntology.ai/paper/2301.08243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.08243"}},"official":{"repos":["facebookresearch/ijepa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/synbols-probing-learning-algorithms-with","slug":"synbols-probing-learning-algorithms-with","title":"Synbols: Probing Learning Algorithms with Synthetic Datasets","date":"2020-09-14","arxiv_id":"2009.06415","repositories_listed":4,"syntology":null},{"url":"/paper/visionreasoner-unified-visual-perception-and","slug":"visionreasoner-unified-visual-perception-and","title":"VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning","date":"2025-05-17","arxiv_id":"2505.12081","repositories_listed":3,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/visionreasoner-unified-visual-perception-and#ran","syntology_url":"https://syntology.ai/paper/2505.12081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12081"}},"official":{"repos":["dvlab-research/VisionReasoner","hiyouga/easyr1","dvlab-research/Seg-Zero"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-pear-fruit-detection-and-counting","slug":"real-time-pear-fruit-detection-and-counting","title":"Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT","date":"2021-07-14","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/cnn-based-density-estimation-and-crowd","slug":"cnn-based-density-estimation-and-crowd","title":"CNN-based Density Estimation and Crowd Counting: A Survey","date":"2020-03-28","arxiv_id":"2003.12783","repositories_listed":3,"syntology":null},{"url":"/paper/from-open-set-to-closed-set-supervised","slug":"from-open-set-to-closed-set-supervised","title":"From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting","date":"2020-01-07","arxiv_id":"2001.01886","repositories_listed":3,"syntology":null},{"url":"/paper/where-are-the-blobs-counting-by-localization","slug":"where-are-the-blobs-counting-by-localization","title":"Where are the Blobs: Counting by Localization with Point Supervision","date":"2018-07-25","arxiv_id":"1807.09856","repositories_listed":3,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/where-are-the-blobs-counting-by-localization#ran","syntology_url":"https://syntology.ai/paper/1807.09856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09856"}},"official":null}},{"url":"/paper/vision-transformers-for-weakly-supervised","slug":"vision-transformers-for-weakly-supervised","title":"Vision Transformers for Weakly-Supervised Microorganism Enumeration","date":"2024-12-03","arxiv_id":"2412.02250","repositories_listed":2,"syntology":null},{"url":"/paper/countgd-multi-modal-open-world-counting","slug":"countgd-multi-modal-open-world-counting","title":"CountGD: Multi-Modal Open-World Counting","date":"2024-07-05","arxiv_id":"2407.04619","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_constructed":1,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/countgd-multi-modal-open-world-counting#ran","syntology_url":"https://syntology.ai/paper/2407.04619","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04619"}},"official":null}},{"url":"/paper/learning-to-count-anything-reference-less","slug":"learning-to-count-anything-reference-less","title":"Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision","date":"2022-05-20","arxiv_id":"2205.10203","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-to-count-anything-reference-less#ran","syntology_url":"https://syntology.ai/paper/2205.10203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10203"}},"official":{"repos":["activevisionlab/learningtocountanything"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dall-eval-probing-the-reasoning-skills-and","slug":"dall-eval-probing-the-reasoning-skills-and","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","date":"2022-02-08","arxiv_id":"2202.04053","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dall-eval-probing-the-reasoning-skills-and#ran","syntology_url":"https://syntology.ai/paper/2202.04053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04053"}},"official":{"repos":["j-min/dalleval"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-domain-adaptation-for-plant","slug":"unsupervised-domain-adaptation-for-plant","title":"Unsupervised Domain Adaptation For Plant Organ Counting","date":"2020-09-02","arxiv_id":"2009.01081","repositories_listed":2,"syntology":null},{"url":"/paper/encoder-decoder-based-convolutional-neural","slug":"encoder-decoder-based-convolutional-neural","title":"Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting","date":"2020-03-12","arxiv_id":"2003.05586","repositories_listed":2,"syntology":null},{"url":"/paper/drone-based-rgbt-vehicle-detection-and","slug":"drone-based-rgbt-vehicle-detection-and","title":"Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning","date":"2020-03-05","arxiv_id":"2003.02437","repositories_listed":2,"syntology":null},{"url":"/paper/object-counting-and-instance-segmentation","slug":"object-counting-and-instance-segmentation","title":"Object Counting and Instance Segmentation with Image-level Supervision","date":"2019-03-06","arxiv_id":"1903.02494","repositories_listed":2,"syntology":null},{"url":"/paper/improving-object-counting-with-heatmap","slug":"improving-object-counting-with-heatmap","title":"Improving Object Counting with Heatmap Regulation","date":"2018-03-14","arxiv_id":"1803.05494","repositories_listed":2,"syntology":null},{"url":"/paper/towards-perspective-free-object-counting-with","slug":"towards-perspective-free-object-counting-with","title":"Towards perspective-free object counting with deep learning","date":"2016-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/car-object-counting-and-position-estimation","slug":"car-object-counting-and-position-estimation","title":"Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework","date":"2025-07-11","arxiv_id":"2507.08240","repositories_listed":1,"syntology":null},{"url":"/paper/improving-contrastive-learning-for-referring","slug":"improving-contrastive-learning-for-referring","title":"Improving Contrastive Learning for Referring Expression Counting","date":"2025-05-28","arxiv_id":"2505.22850","repositories_listed":1,"syntology":null},{"url":"/paper/instructsam-a-training-free-framework-for","slug":"instructsam-a-training-free-framework-for","title":"InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition","date":"2025-05-21","arxiv_id":"2505.15818","repositories_listed":1,"syntology":null},{"url":"/paper/save-self-attention-on-visual-embedding-for","slug":"save-self-attention-on-visual-embedding-for","title":"SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting","date":"2025-02-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/t2icount-enhancing-cross-modal-understanding","slug":"t2icount-enhancing-cross-modal-understanding","title":"T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/geobench-vlm-benchmarking-vision-language","slug":"geobench-vlm-benchmarking-vision-language","title":"GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks","date":"2024-11-28","arxiv_id":"2411.19325","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/geobench-vlm-benchmarking-vision-language#ran","syntology_url":"https://syntology.ai/paper/2411.19325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19325"}},"official":{"repos":["the-ai-alliance/geo-bench-vlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-novel-unified-architecture-for-low-shot","slug":"a-novel-unified-architecture-for-low-shot","title":"A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation","date":"2024-09-27","arxiv_id":"2409.18686","repositories_listed":1,"syntology":null},{"url":"/paper/mind-the-prompt-a-novel-benchmark-for-prompt","slug":"mind-the-prompt-a-novel-benchmark-for-prompt","title":"Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Counting","date":"2024-09-24","arxiv_id":"2409.15953","repositories_listed":1,"syntology":null},{"url":"/paper/dense-center-direction-regression-for-object","slug":"dense-center-direction-regression-for-object","title":"Dense Center-Direction Regression for Object Counting and Localization with Point Supervision","date":"2024-08-26","arxiv_id":"2408.14457","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-object-counting-with-good-exemplars","slug":"zero-shot-object-counting-with-good-exemplars","title":"Zero-shot Object Counting with Good Exemplars","date":"2024-07-06","arxiv_id":"2407.04948","repositories_listed":1,"syntology":null},{"url":"/paper/rs-agent-automating-remote-sensing-tasks","slug":"rs-agent-automating-remote-sensing-tasks","title":"RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent","date":"2024-06-11","arxiv_id":"2406.07089","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rs-agent-automating-remote-sensing-tasks#ran","syntology_url":"https://syntology.ai/paper/2406.07089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07089"}},"official":{"repos":["intellisensing/rs-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-spatial-similarity-distribution-for","slug":"learning-spatial-similarity-distribution-for","title":"Learning Spatial Similarity Distribution for Few-shot Object Counting","date":"2024-05-20","arxiv_id":"2405.11770","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-spatial-similarity-distribution-for#ran","syntology_url":"https://syntology.ai/paper/2405.11770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11770"}},"official":{"repos":["CBalance/SSD"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dave-a-detect-and-verify-paradigm-for-low","slug":"dave-a-detect-and-verify-paradigm-for-low","title":"DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting","date":"2024-04-25","arxiv_id":"2404.16622","repositories_listed":1,"syntology":{"n":18,"n_ran":16,"n_constructed":10,"n_ran_checked":14,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"16 ran (of which 10 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dave-a-detect-and-verify-paradigm-for-low#ran","syntology_url":"https://syntology.ai/paper/2404.16622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16622"}},"official":{"repos":["jerpelhan/dave"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":10,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/change-agent-towards-interactive","slug":"change-agent-towards-interactive","title":"Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis","date":"2024-03-28","arxiv_id":"2403.19646","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-object-localization","slug":"few-shot-object-localization","title":"Few-shot Object Localization","date":"2024-03-19","arxiv_id":"2403.12466","repositories_listed":1,"syntology":null},{"url":"/paper/griffon-v2-advancing-multimodal-perception","slug":"griffon-v2-advancing-multimodal-perception","title":"Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring","date":"2024-03-14","arxiv_id":"2403.09333","repositories_listed":1,"syntology":null},{"url":"/paper/afreeca-annotation-free-counting-for-all","slug":"afreeca-annotation-free-counting-for-all","title":"AFreeCA: Annotation-Free Counting for All","date":"2024-03-07","arxiv_id":"2403.04943","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/afreeca-annotation-free-counting-for-all#ran","syntology_url":"https://syntology.ai/paper/2403.04943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04943"}},"official":{"repos":["adrian-dalessandro/afreeca"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/nwpu-moc-a-benchmark-for-fine-grained-multi","slug":"nwpu-moc-a-benchmark-for-fine-grained-multi","title":"NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Images","date":"2024-01-19","arxiv_id":"2401.10530","repositories_listed":1,"syntology":null},{"url":"/paper/point-segment-and-count-a-generalized-1","slug":"point-segment-and-count-a-generalized-1","title":"Point Segment and Count: A Generalized Framework for Object Counting","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vlcounter-text-aware-visual-representation","slug":"vlcounter-text-aware-visual-representation","title":"VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting","date":"2023-12-27","arxiv_id":"2312.16580","repositories_listed":1,"syntology":null},{"url":"/paper/earthvqa-towards-queryable-earth-via","slug":"earthvqa-towards-queryable-earth-via","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","date":"2023-12-19","arxiv_id":"2312.12222","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/earthvqa-towards-queryable-earth-via#ran","syntology_url":"https://syntology.ai/paper/2312.12222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12222"}},"official":{"repos":["Junjue-Wang/EarthVQA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/point-segment-and-count-a-generalized","slug":"point-segment-and-count-a-generalized","title":"Point, Segment and Count: A Generalized Framework for Object Counting","date":"2023-11-21","arxiv_id":"2311.12386","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-generative-augmentations-for-few","slug":"semantic-generative-augmentations-for-few","title":"Semantic Generative Augmentations for Few-Shot Counting","date":"2023-10-26","arxiv_id":"2311.16122","repositories_listed":1,"syntology":null},{"url":"/paper/steerer-resolving-scale-variations-for","slug":"steerer-resolving-scale-variations-for","title":"STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning","date":"2023-08-21","arxiv_id":"2308.10468","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/steerer-resolving-scale-variations-for#ran","syntology_url":"https://syntology.ai/paper/2308.10468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10468"}},"official":{"repos":["taohan10200/steerer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/semantic-counting-from-self-collages","slug":"semantic-counting-from-self-collages","title":"Learning to Count without Annotations","date":"2023-07-17","arxiv_id":"2307.08727","repositories_listed":1,"syntology":null},{"url":"/paper/training-free-object-counting-with-prompts","slug":"training-free-object-counting-with-prompts","title":"Training-free Object Counting with Prompts","date":"2023-06-30","arxiv_id":"2307.00038","repositories_listed":1,"syntology":null},{"url":"/paper/remoteclip-a-vision-language-foundation-model","slug":"remoteclip-a-vision-language-foundation-model","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","date":"2023-06-19","arxiv_id":"2306.11029","repositories_listed":1,"syntology":null},{"url":"/paper/open-world-text-specified-object-counting","slug":"open-world-text-specified-object-counting","title":"Open-world Text-specified Object Counting","date":"2023-06-02","arxiv_id":"2306.01851","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-for-good-visual-tokenizers-for","slug":"what-makes-for-good-visual-tokenizers-for","title":"What Makes for Good Visual Tokenizers for Large Language Models?","date":"2023-05-20","arxiv_id":"2305.12223","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-makes-for-good-visual-tokenizers-for#ran","syntology_url":"https://syntology.ai/paper/2305.12223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12223"}},"official":{"repos":["tencentarc/gvt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/clip-count-towards-text-guided-zero-shot","slug":"clip-count-towards-text-guided-zero-shot","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","date":"2023-05-12","arxiv_id":"2305.07304","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-count-towards-text-guided-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2305.07304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07304"}},"official":{"repos":["songrise/clip-count"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-transformer-off-the-shelf-a-surprising","slug":"vision-transformer-off-the-shelf-a-surprising","title":"Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting","date":"2023-05-08","arxiv_id":"2305.04440","repositories_listed":1,"syntology":null},{"url":"/paper/indiscernible-object-counting-in-underwater","slug":"indiscernible-object-counting-in-underwater","title":"RGB-D Indiscernible Object Counting in Underwater Scenes","date":"2023-04-23","arxiv_id":"2304.11677","repositories_listed":1,"syntology":null},{"url":"/paper/can-sam-count-anything-an-empirical-study-on","slug":"can-sam-count-anything-an-empirical-study-on","title":"Can SAM Count Anything? An Empirical Study on SAM Counting","date":"2023-04-21","arxiv_id":"2304.10817","repositories_listed":1,"syntology":null},{"url":"/paper/tifa-accurate-and-interpretable-text-to-image","slug":"tifa-accurate-and-interpretable-text-to-image","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","date":"2023-03-21","arxiv_id":"2303.11897","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tifa-accurate-and-interpretable-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2303.11897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11897"}},"official":{"repos":["Yushi-Hu/tifa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-object-counting","slug":"zero-shot-object-counting","title":"Zero-shot Object Counting","date":"2023-03-03","arxiv_id":"2303.02001","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/zero-shot-object-counting#ran","syntology_url":"https://syntology.ai/paper/2303.02001","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02001"}},"official":{"repos":["cvlab-stonybrook/zero-shot-counting"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/teaching-clip-to-count-to-ten","slug":"teaching-clip-to-count-to-ten","title":"Teaching CLIP to Count to Ten","date":"2023-02-23","arxiv_id":"2302.12066","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/teaching-clip-to-count-to-ten#ran","syntology_url":"https://syntology.ai/paper/2302.12066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12066"}},"official":null}},{"url":"/paper/a-unified-object-counting-network-with-object","slug":"a-unified-object-counting-network-with-object","title":"A Unified Object Counting Network with Object Occupation Prior","date":"2022-12-29","arxiv_id":"2212.14193","repositories_listed":1,"syntology":null},{"url":"/paper/scale-prior-deformable-convolution-for","slug":"scale-prior-deformable-convolution-for","title":"Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting","date":"2022-12-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/roboflow-100-a-rich-multi-domain-object","slug":"roboflow-100-a-rich-multi-domain-object","title":"Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark","date":"2022-11-24","arxiv_id":"2211.13523","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/roboflow-100-a-rich-multi-domain-object#ran","syntology_url":"https://syntology.ai/paper/2211.13523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13523"}},"official":{"repos":["roboflow-ai/roboflow-100-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-low-shot-object-counting-network-with","slug":"a-low-shot-object-counting-network-with","title":"A Low-Shot Object Counting Network With Iterative Prototype Adaptation","date":"2022-11-15","arxiv_id":"2211.08217","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-low-shot-object-counting-network-with#ran","syntology_url":"https://syntology.ai/paper/2211.08217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08217"}},"official":{"repos":["djukicn/loca"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/countr-transformer-based-generalised-visual","slug":"countr-transformer-based-generalised-visual","title":"CounTR: Transformer-based Generalised Visual Counting","date":"2022-08-29","arxiv_id":"2208.13721","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/countr-transformer-based-generalised-visual#ran","syntology_url":"https://syntology.ai/paper/2208.13721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.13721"}},"official":{"repos":["Verg-Avesta/CounTR"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/few-shot-object-counting-and-detection","slug":"few-shot-object-counting-and-detection","title":"Few-shot Object Counting and Detection","date":"2022-07-22","arxiv_id":"2207.10988","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-object-counting-and-detection#ran","syntology_url":"https://syntology.ai/paper/2207.10988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10988"}},"official":{"repos":["vinairesearch/counting-detr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-spatial-invariance-of-1","slug":"rethinking-spatial-invariance-of-1","title":"Rethinking Spatial Invariance of Convolutional Networks for Object Counting","date":"2022-06-10","arxiv_id":"2206.05253","repositories_listed":1,"syntology":null},{"url":"/paper/represent-compare-and-learn-a-similarity","slug":"represent-compare-and-learn-a-similarity","title":"Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting","date":"2022-03-16","arxiv_id":"2203.08354","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/represent-compare-and-learn-a-similarity#ran","syntology_url":"https://syntology.ai/paper/2203.08354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08354"}},"official":{"repos":["flyinglynx/Bilinear-Matching-Network"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/counting-with-adaptive-auxiliary-learning","slug":"counting-with-adaptive-auxiliary-learning","title":"Counting with Adaptive Auxiliary Learning","date":"2022-03-08","arxiv_id":"2203.04061","repositories_listed":1,"syntology":null},{"url":"/paper/domain-randomization-for-object-counting","slug":"domain-randomization-for-object-counting","title":"Domain Randomization for Object Counting","date":"2022-02-17","arxiv_id":"2202.08670","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-correlation-based-feature","slug":"iterative-correlation-based-feature","title":"Few-shot Object Counting with Similarity-Aware Feature Enhancement","date":"2022-01-22","arxiv_id":"2201.08959","repositories_listed":1,"syntology":null},{"url":"/paper/is-count-large-scale-object-counting-from","slug":"is-count-large-scale-object-counting-from","title":"IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling","date":"2021-12-16","arxiv_id":"2112.09126","repositories_listed":1,"syntology":null},{"url":"/paper/automating-cell-counting-in-fluorescent","slug":"automating-cell-counting-in-fluorescent","title":"Automating cell counting in fluorescent microscopy through deep learning with c-ResUnet","date":"2021-11-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-accurate-car-counting-in-aerial-images","slug":"an-accurate-car-counting-in-aerial-images","title":"An Accurate Car Counting in Aerial Images Based on Convolutional Neural Networks","date":"2021-07-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/spatial-temporal-super-resolution-of","slug":"spatial-temporal-super-resolution-of","title":"Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis","date":"2021-06-22","arxiv_id":"2106.11485","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatial-temporal-super-resolution-of#ran","syntology_url":"https://syntology.ai/paper/2106.11485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11485"}},"official":{"repos":["KellyYutongHe/satellite-pixel-synthesis-pytorch"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/class-agnostic-few-shot-object-counting","slug":"class-agnostic-few-shot-object-counting","title":"Class-agnostic-Few-shot-Object-Counting","date":"2021-06-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-count-everything","slug":"learning-to-count-everything","title":"Learning To Count Everything","date":"2021-04-16","arxiv_id":"2104.08391","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-to-count-everything#ran","syntology_url":"https://syntology.ai/paper/2104.08391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08391"}},"official":{"repos":["cvlab-stonybrook/LearningToCountEverything"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/image-augmentation-for-multitask-few-shot","slug":"image-augmentation-for-multitask-few-shot","title":"Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-Case","date":"2021-02-24","arxiv_id":"2102.12295","repositories_listed":1,"syntology":null},{"url":"/paper/heatmap-based-object-detection-and-tracking","slug":"heatmap-based-object-detection-and-tracking","title":"Heatmap-based Object Detection and Tracking with a Fully Convolutional Neural Network","date":"2021-01-10","arxiv_id":"2101.03541","repositories_listed":1,"syntology":null},{"url":"/paper/pscnet-pyramidal-scale-and-global-context","slug":"pscnet-pyramidal-scale-and-global-context","title":"PSGCNet: A Pyramidal Scale and Global Context Guided Network for Dense Object Counting in Remote Sensing Images","date":"2020-12-07","arxiv_id":"2012.03597","repositories_listed":1,"syntology":null},{"url":"/paper/counting-from-sky-a-large-scale-dataset-for","slug":"counting-from-sky-a-large-scale-dataset-for","title":"Counting from Sky: A Large-scale Dataset for Remote Sensing Object Counting and A Benchmark Method","date":"2020-08-28","arxiv_id":"2008.12470","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-modulated-convolutions-for-visual","slug":"revisiting-modulated-convolutions-for-visual","title":"MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond","date":"2020-04-24","arxiv_id":"2004.11883","repositories_listed":1,"syntology":null},{"url":"/paper/towards-partial-supervision-for-generic","slug":"towards-partial-supervision-for-generic","title":"Towards Partial Supervision for Generic Object Counting in Natural Scenes","date":"2019-12-13","arxiv_id":"1912.06448","repositories_listed":1,"syntology":null},{"url":"/paper/class-agnostic-counting","slug":"class-agnostic-counting","title":"Class-Agnostic Counting","date":"2018-11-01","arxiv_id":"1811.00472","repositories_listed":1,"syntology":null},{"url":"/paper/tallyqa-answering-complex-counting-questions","slug":"tallyqa-answering-complex-counting-questions","title":"TallyQA: Answering Complex Counting Questions","date":"2018-10-29","arxiv_id":"1810.12440","repositories_listed":1,"syntology":null},{"url":"/paper/counting-everyday-objects-in-everyday-scenes","slug":"counting-everyday-objects-in-everyday-scenes","title":"Counting Everyday Objects in Everyday Scenes","date":"2016-04-12","arxiv_id":"1604.03505","repositories_listed":1,"syntology":null},{"url":null,"slug":"omnispatial-towards-comprehensive-spatial","title":"OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models","date":"2025-06-03","arxiv_id":"2506.03135","repositories_listed":0,"syntology":null},{"url":null,"slug":"expanding-zero-shot-object-counting-with-rich","title":"Expanding Zero-Shot Object Counting with Rich Prompts","date":"2025-05-21","arxiv_id":"2505.15398","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-multimodal-large-language-models-ready","title":"Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?","date":"2025-05-17","arxiv_id":"2505.11907","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-what-not-to-count","title":"Learning What NOT to Count","date":"2025-04-16","arxiv_id":"2504.11705","repositories_listed":0,"syntology":null},{"url":null,"slug":"marmot-multi-agent-reasoning-for-multi-object","title":"Marmot: Multi-Agent Reasoning for Multi-Object Self-Correcting in Improving Image-Text Alignment","date":"2025-04-10","arxiv_id":"2504.20054","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathglance-multimodal-large-language-models","title":"MATHGLANCE: Multimodal Large Language Models Do Not Know Where to Look in Mathematical Diagrams","date":"2025-03-26","arxiv_id":"2503.20745","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-causal-lens-for-evaluating-faithfulness","title":"A Causal Lens for Evaluating Faithfulness Metrics","date":"2025-02-26","arxiv_id":"2502.18848","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-vision-language-models-struggle-with","title":"Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding","date":"2025-02-17","arxiv_id":"2502.11492","repositories_listed":0,"syntology":null},{"url":null,"slug":"focalcount-towards-class-count-imbalance-in","title":"FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting","date":"2025-02-15","arxiv_id":"2502.10677","repositories_listed":0,"syntology":null},{"url":null,"slug":"aquaticclip-a-vision-language-foundation","title":"AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis","date":"2025-02-03","arxiv_id":"2502.01785","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-class-agnostic-counting","title":"A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches","date":"2025-01-31","arxiv_id":"2501.19184","repositories_listed":0,"syntology":null},{"url":null,"slug":"mamba-moc-a-multicategory-remote-object","title":"Mamba-MOC: A Multicategory Remote Object Counting via State Space Model","date":"2025-01-12","arxiv_id":"2501.06697","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-alignment-enhanced-adaptive","title":"Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension","date":"2025-01-02","arxiv_id":"2501.01416","repositories_listed":0,"syntology":null},{"url":null,"slug":"counting-stacked-objects-from-multi-view","title":"Counting Stacked Objects from Multi-View Images","date":"2024-11-28","arxiv_id":"2411.19149","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-masked-autoencoder-for-video-object","title":"Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark","date":"2024-11-20","arxiv_id":"2411.13056","repositories_listed":0,"syntology":null},{"url":null,"slug":"boundary-attention-constrained-zero-shot","title":"Boundary Attention Constrained Zero-Shot Layout-To-Image Generation","date":"2024-11-15","arxiv_id":"2411.10495","repositories_listed":0,"syntology":null},{"url":"/paper/gca-sun-a-gated-context-aware-swin-unet-for","slug":"gca-sun-a-gated-context-aware-swin-unet-for","title":"GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting","date":"2024-09-18","arxiv_id":"2409.12249","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-object-count-optimization-for-text","title":"Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models","date":"2024-08-21","arxiv_id":"2408.11721","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutually-aware-feature-learning-for-few-shot","title":"Mutually-Aware Feature Learning for Few-Shot Object Counting","date":"2024-08-19","arxiv_id":"2408.09734","repositories_listed":0,"syntology":null}],"syntology_records":27,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":24,"papers_where_code_ran_first_page":"/task/object-counting/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/object-counting/papers/2","json":"/task/object-counting/papers/2.json","rows":58},{"order":"ran","page":1,"of":1,"url":"/task/object-counting/papers/ran/1","json":"/task/object-counting/papers/ran/1.json","rows":24}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"a56c21735eb503e17404cb9c38732c8bacb4bacd11f8f85ef756e6308cef1d88","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}