{"id":"W2133566984","doi":"10.1109/tpami.2002.1008387","title":"Adjusting shape parameters using model-based optical flow residuals","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Technical University of Athens; University of Toronto; University of Pennsylvania","keywords":"Optical flow; Computation; Flow (mathematics); Computer science; Least-squares function approximation; Face (sociological concept); Artificial intelligence; Algorithm; Tracking (education); Computer vision; Mathematics; Image (mathematics); Statistics; Geometry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002008272,0.0002454854,0.0003254783,0.0006905724,0.0003213665,0.0001931464,0.0004114831,0.00005629914,0.000162951],"category_scores_gemma":[0.00001208078,0.0002218727,0.000248021,0.001310079,0.00008705921,0.0003762717,0.000007772901,0.0003078186,0.00002324494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004019327,"about_ca_system_score_gemma":0.00001238447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008170017,"about_ca_topic_score_gemma":0.00004717362,"domain_scores_codex":[0.9982216,0.00006813549,0.0004159677,0.0006319212,0.0003281154,0.0003342221],"domain_scores_gemma":[0.9989682,0.0001555249,0.00009616447,0.0005177047,0.00007081276,0.0001915363],"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":[0.000001561682,0.00005238095,0.00002998258,0.000004538552,0.00004838192,0.000005401737,0.00007670072,0.4992987,0.0002579677,0.000007748182,0.000001108501,0.5002155],"study_design_scores_gemma":[0.00008389175,0.00004475392,0.00002246047,0.00003331993,0.0002056795,0.00000740147,0.00001857157,0.9426645,0.05655027,0.0001224026,0.000005135673,0.00024162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002729836,0.0001039926,0.9963902,0.0004022696,0.0000970339,0.00008509011,0.00001302117,0.0001117807,0.0000667427],"genre_scores_gemma":[0.7639714,0.00007270167,0.2350192,0.0008570273,0.000007137949,0.000005621607,9.583327e-7,0.00001096952,0.00005496388],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.761371,"threshold_uncertainty_score":0.9047707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05364459216019008,"score_gpt":0.3029724265634319,"score_spread":0.2493278344032419,"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."}}