{"id":"W2106364358","doi":"10.1109/3dim.2005.81","title":"Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets","year":2005,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":246,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"RANSAC; Artificial intelligence; Computer vision; Computer science; Bundle adjustment; Perspective (graphical); Object (grammar); Scale-invariant feature transform; Invariant (physics); Cognitive neuroscience of visual object recognition; Constraint (computer-aided design); Translation (biology); Rotation (mathematics); Matching (statistics); Pattern recognition (psychology); Structure from motion; Image (mathematics); Motion (physics); Mathematics","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":[0.00005662749,0.0000687806,0.00007069601,0.00009378753,0.00001898194,0.00002291918,0.00001992568,0.00005240212,0.0001500966],"category_scores_gemma":[0.00001147088,0.00007175461,0.000007863922,0.0001166391,0.00001061333,0.000164787,0.000004687497,0.00005524259,0.00003552512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003102915,"about_ca_system_score_gemma":0.000004421977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004602164,"about_ca_topic_score_gemma":0.0004236892,"domain_scores_codex":[0.9996023,0.00001397021,0.0001413747,0.0001005821,0.00004416691,0.00009765972],"domain_scores_gemma":[0.9998571,0.00001606385,0.000008169422,0.00007760349,0.00001170418,0.00002935832],"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":[0.00001260286,0.00002438312,0.001407213,0.00004941068,0.00001274159,0.000002643916,0.0001352741,0.2166062,0.00435164,0.00005949966,0.0008002729,0.7765381],"study_design_scores_gemma":[0.0006544666,0.00001567359,0.00193595,0.00003074424,0.000006927593,0.0000181728,0.00006795635,0.9917852,0.00374164,0.0002062318,0.001371374,0.0001656512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9671136,0.0001486707,0.02759487,0.0001101651,0.0001634583,0.0001829745,0.00007034431,0.000215141,0.004400837],"genre_scores_gemma":[0.9864438,0.000295293,0.01250786,0.00007127683,0.00005523484,0.000004491815,0.0005879449,0.00001531094,0.0000187641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7763724,"threshold_uncertainty_score":0.2926068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01684215282834634,"score_gpt":0.2009661604307633,"score_spread":0.184124007602417,"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."}}