{"id":"W2132284553","doi":"10.1109/icpr.2008.4761488","title":"Real-time foreground segmentation on GPUs using local online learning and global graph cut optimization","year":2008,"lang":"en","type":"article","venue":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Pixel; Graphics processing unit; Graphics; Segmentation; Artificial intelligence; Graph; Perspective (graphical); Cut; Image segmentation; General-purpose computing on graphics processing units; Computer vision; Machine learning; Computer graphics (images); Theoretical computer science; Parallel computing","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000823111,0.001071324,0.0007441017,0.001156649,0.0007608894,0.00160212,0.001323987,0.0004645657,0.001116387],"category_scores_gemma":[0.0003040194,0.001150976,0.0002974612,0.0007113183,0.0003371775,0.002993482,0.000353813,0.00105522,0.0003796786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008569426,"about_ca_system_score_gemma":0.0001739757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002371854,"about_ca_topic_score_gemma":0.00003381405,"domain_scores_codex":[0.9932734,0.00009390456,0.001344218,0.00218155,0.002218878,0.00088806],"domain_scores_gemma":[0.9936801,0.0001827518,0.001378924,0.0001956864,0.004138293,0.0004243025],"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":[0.001425115,0.002431025,0.06508668,0.0002831582,0.001086481,0.0001438496,0.002030129,0.0008371826,0.01062765,0.01316338,0.0006968401,0.9021885],"study_design_scores_gemma":[0.007300123,0.002904259,0.02072326,0.00373392,0.0001905985,0.001286137,0.00271587,0.9147005,0.0157237,0.02701657,0.0001633781,0.003541684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7129098,0.000009605764,0.2392499,0.002314791,0.001713253,0.0009650519,0.0006738867,0.0007708126,0.04139292],"genre_scores_gemma":[0.9780123,0.001392321,0.01627412,0.001277527,0.0008084579,0.0002026101,0.001683087,0.0001013692,0.0002482047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9138633,"threshold_uncertainty_score":0.9997967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09196735871716002,"score_gpt":0.3315644954189243,"score_spread":0.2395971367017643,"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."}}