{"id":"W1602810076","doi":"10.1109/icra.2015.7139965","title":"Keypoint matching by outlier pruning with consensus constraint","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Matching (statistics); Outlier; Optical flow; Artificial intelligence; Pruning; Computer vision; Displacement (psychology); Computer science; Constraint (computer-aided design); Pattern recognition (psychology); Image (mathematics); Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002178359,0.0001084465,0.0001142948,0.00004122717,0.00007132421,0.0001435612,0.000277986,0.00001774339,0.00001694727],"category_scores_gemma":[0.00002975247,0.00007729056,0.00001739747,0.0001351677,0.00006410007,0.0002513595,0.000145047,0.0001188476,0.00009437265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003315997,"about_ca_system_score_gemma":0.00008751606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000288616,"about_ca_topic_score_gemma":0.000004651317,"domain_scores_codex":[0.9990923,0.00002952251,0.0001406925,0.0002703345,0.0002314361,0.0002357263],"domain_scores_gemma":[0.9993218,0.00004180126,0.00005340064,0.000298049,0.00008847713,0.0001964925],"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":[0.00005033105,0.0002125936,0.001831874,0.0000211192,0.0000649213,0.0003161532,0.009689525,0.003481601,0.006177622,0.2341681,0.1215783,0.6224079],"study_design_scores_gemma":[0.004791358,0.000501071,0.0001684151,0.0002026161,0.00001250468,0.001154996,0.008347918,0.6528691,0.01363403,0.02155431,0.295291,0.001472681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003231362,0.00005952715,0.9565218,0.003223803,0.000134154,0.00007903943,8.47972e-7,0.0002643618,0.03648511],"genre_scores_gemma":[0.4313099,9.173869e-7,0.5657514,0.001504004,0.00001542725,0.000002214076,8.349071e-7,0.000007553319,0.001407672],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6493875,"threshold_uncertainty_score":0.3151818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02175306629990937,"score_gpt":0.2630792504310589,"score_spread":0.2413261841311495,"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."}}