{"id":"W3101113336","doi":"10.1109/wacv48630.2021.00155","title":"Deep Template-based Object Instance Detection","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Scan|Design Fonden v. Inger og Jens Bruun; Nvidia","keywords":"Artificial intelligence; Computer science; Object (grammar); Viewpoints; Object detection; Computer vision; Focus (optics); Context (archaeology); Minimum bounding box; Class (philosophy); Cognitive neuroscience of visual object recognition; Matching (statistics); Viola–Jones object detection framework; Process (computing); Pattern recognition (psychology); Image (mathematics); Face detection; Mathematics; Facial recognition system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005447657,0.001652582,0.001672576,0.001108008,0.0003175957,0.001384036,0.004364138,0.001582026,0.004907464],"category_scores_gemma":[0.001258189,0.0006874668,0.001222027,0.001295772,0.0004492634,0.00201248,0.001776262,0.001479941,0.004965375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008508267,"about_ca_system_score_gemma":0.000811253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005405131,"about_ca_topic_score_gemma":0.01014913,"domain_scores_codex":[0.9992898,0.00003992585,0.00002283265,0.0003427262,0.0001837873,0.0001209204],"domain_scores_gemma":[0.999432,0.00007350397,0.00006148255,0.000259868,0.0001201423,0.00005297696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002561931,0.0002267938,0.002133508,0.000176149,0.0001916831,0.0001598469,0.00005118689,0.0537181,0.04793621,0.003099994,0.02006364,0.8719866],"study_design_scores_gemma":[0.00001811064,0.00009581696,0.001384916,0.00002269991,0.00004600524,0.0003856246,0.00002287108,0.9420921,0.04508098,0.004240128,0.006585269,0.00002544506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02607641,0.0008553235,0.9468224,0.0001228352,0.000160147,0.0001150842,0.001168414,0.02144493,0.003234403],"genre_scores_gemma":[0.2475681,0.000734028,0.7317531,0.0003760264,0.0001006503,0.0001461611,0.007406371,0.0007602155,0.01115526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005405131,"threshold_uncertainty_score":0.01641709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02146998178595112,"score_gpt":0.2647182299016234,"score_spread":0.2432482481156722,"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."}}