{"id":"W4237709258","doi":"10.1109/cvprw.2009.5206728","title":"Spatiotemporal stereo via spatiotemporal quadric element (stequel) matching","year":2009,"lang":"en","type":"article","venue":"2009 IEEE Conference on Computer Vision and Pattern Recognition","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Artificial intelligence; Coherence (philosophical gambling strategy); Computer vision; Matching (statistics); Ground truth; Sequence (biology); Quadric; Motion estimation; Pattern recognition (psychology); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003117636,0.0003991486,0.0003526558,0.0003189839,0.0002562109,0.0005814136,0.0004457824,0.0001113241,0.00009836699],"category_scores_gemma":[0.000004826865,0.0003588551,0.00009582718,0.0002490855,0.0000378508,0.001135521,0.0001053585,0.0003496272,0.0002627065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000547094,"about_ca_system_score_gemma":0.00004140415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003733324,"about_ca_topic_score_gemma":0.0000112589,"domain_scores_codex":[0.9974653,0.000194999,0.0005694652,0.0008398762,0.0004903799,0.0004399796],"domain_scores_gemma":[0.9987139,0.00006923945,0.0003077988,0.000477093,0.0001841491,0.0002478082],"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":[0.00001709405,0.0001450963,0.0001127036,0.00001581913,0.000006458552,0.00003151712,0.0002766305,0.00002596934,0.0007140751,0.0003087927,0.0004913014,0.9978545],"study_design_scores_gemma":[0.001887345,0.002251018,0.01818028,0.0008356035,0.00001308118,0.00008468668,0.00003524069,0.9454426,0.003025422,0.02606953,0.001125965,0.001049252],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06447709,0.00004093103,0.9311506,0.002226133,0.0008711453,0.0003368163,0.00001137908,0.0002595787,0.0006263921],"genre_scores_gemma":[0.9273703,0.00008678319,0.06723318,0.004944833,0.0002136281,0.000007775814,0.00006351751,0.00001580439,0.00006420955],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9968053,"threshold_uncertainty_score":0.9998863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03999395813345635,"score_gpt":0.2980760253148209,"score_spread":0.2580820671813645,"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."}}