{"id":"W2005332837","doi":"10.1109/tpami.2012.276","title":"FOCUSR: Feature Oriented Correspondence Using Spectral Regularization--A Method for Precise Surface Matching","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; McGill University","funders":"National Institute of Biomedical Imaging and Bioengineering","keywords":"Pattern recognition (psychology); Algorithm; Regularization (linguistics); Computer science; Matching (statistics); Artificial intelligence; Mathematics; Laplace operator; Vertex (graph theory); Feature (linguistics); Graph; Embedding; Feature extraction; Theoretical computer science","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":[0.00056312,0.0002703959,0.0003666791,0.0003569653,0.0003385686,0.0001430619,0.0004068418,0.000086269,0.0000371746],"category_scores_gemma":[0.00001684427,0.0002393571,0.0002731796,0.001487267,0.000042904,0.0009306881,0.00001068311,0.0002856401,0.000003998788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006762752,"about_ca_system_score_gemma":0.00002436383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002356066,"about_ca_topic_score_gemma":0.00007891175,"domain_scores_codex":[0.9983104,0.0001340676,0.0003380365,0.0005296457,0.0002854758,0.000402344],"domain_scores_gemma":[0.9986656,0.0003269836,0.0001656779,0.0005242047,0.000142952,0.0001746031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009197425,0.0002945843,0.000830405,0.00004576527,0.000497736,0.000005921826,0.001162947,0.05959919,0.01504527,0.001186424,0.00002266227,0.9212171],"study_design_scores_gemma":[0.00007590138,0.00008405239,0.0001184733,0.00003054654,0.0003222474,0.00002482913,0.00004411944,0.3420018,0.6557559,0.001107584,0.0001589588,0.0002755545],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00160226,0.0002880603,0.9971262,0.0001820912,0.000257168,0.0003135941,0.00005016814,0.0001651758,0.00001532936],"genre_scores_gemma":[0.6078553,0.0001259336,0.3913746,0.0001540454,0.00002908056,0.00001222088,0.000004993275,0.00001487671,0.000429034],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9209416,"threshold_uncertainty_score":0.97607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02708206847976843,"score_gpt":0.3336913127108676,"score_spread":0.3066092442310991,"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."}}