{"id":"W2124798821","doi":"10.1007/s11760-008-0055-6","title":"Feature-based detection and correction of occlusions and split of video objects","year":2008,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Communications Research Centre Canada","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Feature (linguistics); Segmentation; Tracking (education); Object detection; Video tracking; Superposition principle; Occlusion; Pattern recognition (psychology); Object (grammar); 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":[0.0005110531,0.0001239427,0.0002286293,0.0001500437,0.0002859678,0.00006772789,0.00008721455,0.00007012366,0.000001222177],"category_scores_gemma":[0.0001294062,0.0001109207,0.00003049241,0.0003454966,0.0001965972,0.0006059599,0.00007914197,0.0001319403,1.954837e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008628999,"about_ca_system_score_gemma":0.00007983232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005391482,"about_ca_topic_score_gemma":0.00001955717,"domain_scores_codex":[0.9990904,0.0001085416,0.000183319,0.0003021455,0.0001651273,0.000150513],"domain_scores_gemma":[0.9992648,0.0001938307,0.0001779619,0.0001287447,0.0001688844,0.00006582536],"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":[0.00005318138,0.00004372183,0.00602416,0.0003121078,0.00001126118,0.00001660936,0.001521708,0.00004610323,0.3935434,0.00001721288,0.00003174289,0.5983788],"study_design_scores_gemma":[0.001035123,0.00039582,0.08000427,0.0004733448,0.0000340245,0.0003026155,0.0001508604,0.1835468,0.7327256,0.0008929606,0.0001168362,0.0003217562],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3805757,0.001762688,0.6171536,0.00008634192,0.00008570118,0.00008727173,0.000001216084,0.00004569121,0.0002018798],"genre_scores_gemma":[0.9585077,0.00008514097,0.04126703,0.00007084135,0.00003046067,0.000003340828,6.485424e-7,0.000007328294,0.00002755172],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.598057,"threshold_uncertainty_score":0.4523216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01670772890452617,"score_gpt":0.2703217018152611,"score_spread":0.2536139729107349,"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."}}