{"id":"W2604713725","doi":"10.1109/iccvw.2017.9","title":"Count-ception: Counting by Fully Convolutional Redundant Counting","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Institute for Research in Immunology and Cancer; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Compute Canada; Nvidia; National Science Foundation","keywords":"Convolutional neural network; Computer science; Pixel; Artificial intelligence; Process (computing); Frame (networking); Field (mathematics); Image (mathematics); Computer vision; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001041832,0.0005015684,0.0005403868,0.0001249641,0.0007858558,0.001723849,0.002972655,0.0004223841,0.0001572568],"category_scores_gemma":[0.000287088,0.0004936214,0.000218469,0.0001089526,0.0002652001,0.001088722,0.003083236,0.001031506,0.0001455718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003234162,"about_ca_system_score_gemma":0.0005361268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002047872,"about_ca_topic_score_gemma":0.0000094506,"domain_scores_codex":[0.9964665,0.00006212567,0.0006469203,0.001241636,0.0009604022,0.0006224877],"domain_scores_gemma":[0.9962107,0.0001218238,0.0009060802,0.001839745,0.0007824471,0.0001391948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005997283,0.0004047082,0.002999278,0.0008589712,0.0003234055,0.0001839239,0.0006334547,0.0003096716,0.0147555,0.1094328,0.7607019,0.1093364],"study_design_scores_gemma":[0.0007042616,0.000152271,0.0007699494,0.001032012,0.0000573676,0.0001122575,0.00004294287,0.07595946,0.02315224,0.1032161,0.7923791,0.002422069],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005728552,0.001502591,0.9693235,0.001142351,0.001209506,0.0004445116,0.00006325146,0.001216307,0.0245252],"genre_scores_gemma":[0.3833419,0.002004249,0.5868803,0.001792337,0.00168327,0.0001872242,0.0003617001,0.0001207369,0.02362832],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.382769,"threshold_uncertainty_score":0.9997516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02882587969281593,"score_gpt":0.3100319389745698,"score_spread":0.2812060592817539,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}