{"id":"W2107696950","doi":"10.1109/tpami.2006.232","title":"Optical Flow 3D Segmentation and Interpretation: A Variational Method with Active Curve Evolution and Level Sets","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Optical flow; Segmentation; Artificial intelligence; Motion field; Computer vision; Regularization (linguistics); Computer science; Motion estimation; Image segmentation; Scale-space segmentation; Flow (mathematics); Boundary (topology); Structure from motion; Mathematics; Algorithm; Geometry; Mathematical analysis; Image (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":[0.0001749542,0.0001704829,0.0002008974,0.0003335592,0.0002110076,0.0001496737,0.00009662986,0.00003752932,0.00002677839],"category_scores_gemma":[0.000003962953,0.0001413525,0.00005087541,0.000533884,0.00006698834,0.0006011699,0.000006441211,0.0001653036,0.000002455287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004654349,"about_ca_system_score_gemma":0.00001836974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004339797,"about_ca_topic_score_gemma":0.0005992877,"domain_scores_codex":[0.9988188,0.00009086606,0.0002432192,0.000474393,0.0002305771,0.0001421573],"domain_scores_gemma":[0.9993846,0.0001922437,0.00009006106,0.0001609688,0.00009389474,0.00007821555],"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":[0.00003133668,0.00006591196,0.0004369981,0.000007661416,0.000135701,0.000003068421,0.0003670057,0.04593397,0.0002957526,0.0003693491,0.000001020123,0.9523522],"study_design_scores_gemma":[0.0001722396,0.0001013993,0.01154285,0.0000211638,0.0001948749,0.00003924258,0.00007104575,0.9725834,0.01397716,0.001122285,0.0000045405,0.0001697846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001185999,0.00006227242,0.9980397,0.0004226932,0.00004959025,0.0001134634,0.00003788043,0.00003957329,0.00004888202],"genre_scores_gemma":[0.7395589,0.00003659142,0.2601951,0.0001378169,0.000008027668,0.00001379688,0.000008962708,0.000005125023,0.00003568832],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9521824,"threshold_uncertainty_score":0.5764187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01686855065232622,"score_gpt":0.3011908792969762,"score_spread":0.28432232864465,"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."}}