{"id":"W2096824499","doi":"10.1109/cvpr.2004.402","title":"Motion Segmentation by EM Clustering of Good Features","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Segmentation; Computer science; Artificial intelligence; Image segmentation; Noise (video); Affine transformation; Scale-space segmentation; Pattern recognition (psychology); Independence (probability theory); Computer vision; Algorithm; Mathematics; Image (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":[0.0000467909,0.00003859525,0.00004115313,0.0000300733,0.00002797777,0.00003111943,0.0001330168,0.00001074019,0.00002221808],"category_scores_gemma":[0.000004451825,0.00003336651,0.00001521523,0.00008407181,0.000005040104,0.0005760361,0.00005918116,0.0000289242,0.00001122132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001523801,"about_ca_system_score_gemma":0.000002987426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000378749,"about_ca_topic_score_gemma":0.000005489074,"domain_scores_codex":[0.9996291,0.000009578675,0.00008690991,0.0001054694,0.00009931064,0.00006963436],"domain_scores_gemma":[0.9997979,0.0000093648,0.00003679214,0.0001147376,0.00002002099,0.00002117792],"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":[8.949469e-7,0.00001960269,0.00005857016,0.000003586265,0.000001200614,1.157004e-7,0.0003468902,0.000854234,0.05143333,0.001381133,0.001770819,0.9441296],"study_design_scores_gemma":[0.0003794397,0.00003408308,0.002027258,0.00001176715,0.00000151639,0.000006845718,0.000192031,0.697735,0.2960268,0.00034287,0.003131711,0.0001106494],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002241551,0.00006139158,0.9937688,0.0005495793,0.00006021374,0.00003721484,3.409833e-7,0.00006137951,0.00321957],"genre_scores_gemma":[0.5486235,0.000005367702,0.4498578,0.0003709521,0.00001573133,0.000001002524,0.000001462217,0.00000206685,0.001122146],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.944019,"threshold_uncertainty_score":0.1360647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00803322156187687,"score_gpt":0.2724701303554757,"score_spread":0.2644369087935989,"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."}}