{"id":"W2604233003","doi":"10.1109/cvpr.2017.12","title":"Convolutional Neural Network Architecture for Geometric Matching","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":514,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Canadian Institute for Advanced Research","keywords":"Affine transformation; Computer science; Convolutional neural network; Artificial intelligence; Matching (statistics); Generalization; Pattern recognition (psychology); Transformation (genetics); Feature extraction; Spline (mechanical); Artificial neural network; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005461955,0.00114938,0.0007151387,0.0007720315,0.0003330456,0.0008180306,0.001794886,0.001443731,0.004221088],"category_scores_gemma":[0.001458146,0.0004007931,0.0006685415,0.001219461,0.0004830716,0.001470022,0.0009574895,0.001557615,0.002475518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001208794,"about_ca_system_score_gemma":0.0009178581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009856616,"about_ca_topic_score_gemma":0.0111652,"domain_scores_codex":[0.9995682,0.00005505113,0.00001878908,0.0001672688,0.0001095689,0.00008103631],"domain_scores_gemma":[0.999673,0.00006397966,0.00003410541,0.0001099627,0.00009903526,0.00001998724],"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":[0.0002239685,0.00016137,0.00162434,0.0001667304,0.0001530409,0.0001465993,0.00005568937,0.4406083,0.02263547,0.01351192,0.01126105,0.5094516],"study_design_scores_gemma":[0.000005785563,0.00002727107,0.0003246992,0.000008507018,0.00001640995,0.00004707402,0.000006257977,0.9854279,0.004828221,0.006710213,0.002590027,0.000007642146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03354188,0.001185379,0.9526104,0.0004073337,0.0001372188,0.00007566516,0.0007506932,0.005344159,0.005947246],"genre_scores_gemma":[0.6139911,0.0009780881,0.3661244,0.000424548,0.0001102931,0.0001522917,0.004496926,0.0003043628,0.01341806],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009856616,"threshold_uncertainty_score":0.01959848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03670996608720355,"score_gpt":0.3223604438481787,"score_spread":0.2856504777609752,"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."}}