{"id":"W2163124804","doi":"10.1109/iai.2002.999899","title":"Tracking moving objects as spatio-temporal boundary detection","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Motion estimation; Motion field; Computer vision; Artificial intelligence; Tracking (education); Computer science; Mathematics; Ordinary differential equation; Partial differential equation; Motion (physics); Match moving; Boundary (topology); Structure from motion; Mathematical analysis; Differential equation","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":[0.0001862792,0.00009230745,0.00007964,0.000089621,0.0002444484,0.0002685087,0.0001969449,0.00002580698,0.0000835769],"category_scores_gemma":[0.0001248063,0.00008611177,0.00003945123,0.0002949428,0.00001899022,0.001249025,0.00005171526,0.0001105975,0.0001216154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004490118,"about_ca_system_score_gemma":0.0000648401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003348195,"about_ca_topic_score_gemma":0.00004378976,"domain_scores_codex":[0.9991413,0.00004710246,0.0001445579,0.0002721153,0.0001836699,0.0002112324],"domain_scores_gemma":[0.9995306,0.00003601001,0.00005150502,0.0002588994,0.00005136191,0.0000716494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003872332,0.00004006555,0.001534725,0.000008719836,0.000005641112,0.00002839679,0.000793679,0.000152145,0.00812974,0.02359504,0.0001319715,0.965576],"study_design_scores_gemma":[0.001037144,0.0002145767,0.003279943,0.00006989054,0.000005814302,0.0003127583,0.0006671943,0.3372159,0.4500996,0.06075193,0.1454883,0.0008569931],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01430114,0.00007831554,0.9477949,0.00009786928,0.0004548602,0.00006542739,4.89674e-8,0.0002796285,0.03692779],"genre_scores_gemma":[0.865723,0.000003522691,0.1328736,0.0006438186,0.00002272214,0.000002509672,3.526108e-7,0.000006645562,0.0007239481],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.964719,"threshold_uncertainty_score":0.3511536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01411989355726045,"score_gpt":0.2704233254059921,"score_spread":0.2563034318487316,"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."}}