{"id":"W2121299550","doi":"10.1109/tpami.2007.70752","title":"Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical Priors","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":454,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Carnegie Mellon University","keywords":"Computer science; Artificial intelligence; Computer vision; Face (sociological concept); Prior probability; Motion (physics); Motion estimation; Subspace topology; Point distribution model; Active shape model; Probabilistic logic; Object (grammar); Structure from motion; Shape analysis (program analysis); Rigid transformation; Missing data; Transformation (genetics); Algorithm; Bayesian probability; Machine learning","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":[0.00008012594,0.0002176134,0.0002728099,0.000318055,0.0004078328,0.0001137142,0.0002336782,0.00004449747,0.0001140579],"category_scores_gemma":[0.000004787642,0.0001695158,0.00008443229,0.0007073195,0.0001364654,0.0004475329,0.000008223221,0.0003175054,0.000005321069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002067255,"about_ca_system_score_gemma":0.00001392989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002834488,"about_ca_topic_score_gemma":0.0002307952,"domain_scores_codex":[0.9985685,0.00005949943,0.0002865067,0.0005970466,0.0002864413,0.0002020152],"domain_scores_gemma":[0.9992359,0.0001063802,0.00009591853,0.0003466073,0.00006042922,0.0001547246],"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":[0.000009286911,0.00005178203,0.002014882,0.000006465011,0.0001138856,0.00001914792,0.0005837536,0.02084638,0.0002914835,0.00002616301,9.154093e-7,0.9760358],"study_design_scores_gemma":[0.0001221293,0.00009282141,0.006208151,0.00002671682,0.0001131111,0.00008533052,0.00002455781,0.975156,0.01759261,0.0003462346,0.00001444668,0.0002179003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04929491,0.00006691712,0.9499507,0.0003901345,0.00009627682,0.00008290951,0.00001970994,0.00008218002,0.00001628199],"genre_scores_gemma":[0.9146667,0.0001117401,0.08480793,0.0003392539,0.00002241758,0.000004390705,0.00000539012,0.000009355161,0.00003281735],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.975818,"threshold_uncertainty_score":0.6912652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01685685939758975,"score_gpt":0.2681176636603932,"score_spread":0.2512608042628034,"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."}}