{"id":"W2111110731","doi":"10.1109/icip.2001.958199","title":"A comparative evaluation of algorithms for fast computation of level set PDEs with applications to motion segmentation","year":2002,"lang":"en","type":"article","venue":"","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Computation; Motion (physics); Segmentation; Level set (data structures); Algorithm; Set (abstract data type); Image segmentation; Artificial intelligence; Computer vision","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":[0.0001089518,0.00006603475,0.0001143356,0.00005425312,0.00004611723,0.000007494887,0.00003109776,0.00001295548,0.0001223951],"category_scores_gemma":[6.80934e-7,0.00005678342,0.00003049202,0.0001636042,0.00002022529,0.00007194556,0.000005271791,0.00002174147,0.000003563178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001514917,"about_ca_system_score_gemma":0.00001059258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002604512,"about_ca_topic_score_gemma":0.000005265056,"domain_scores_codex":[0.9994116,0.00003337393,0.0001812156,0.0001256442,0.0001861774,0.00006201037],"domain_scores_gemma":[0.9993356,0.00002133956,0.000135227,0.00006479128,0.0004144061,0.00002856646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000452314,0.0003160322,0.0006918164,0.00002334566,0.00009011212,3.053383e-9,0.002026988,0.5913584,0.006926625,0.005202306,0.001355174,0.391964],"study_design_scores_gemma":[0.0008846496,0.0001541707,0.001151416,0.00001542478,0.00006521759,2.151134e-7,0.001527258,0.9629468,0.03217186,0.0009495436,0.00005080298,0.00008266075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1082066,0.000006297401,0.8894578,0.00006617644,0.00001851433,0.001088101,0.0000598718,0.000006733468,0.001089839],"genre_scores_gemma":[0.9708031,3.908703e-7,0.02845697,0.000009606542,0.00005703055,0.0003521287,0.0001744638,0.000004873713,0.0001414681],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8625965,"threshold_uncertainty_score":0.2315561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2343667734045531,"score_gpt":0.3894535105640143,"score_spread":0.1550867371594612,"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."}}