{"id":"W2109124605","doi":"10.1109/tpami.2003.1206512","title":"A graphical model for audiovisual object tracking","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Graphical model; Artificial intelligence; Video tracking; Computer vision; Exploit; Object (grammar); Tracking (education); Inference; Process (computing); Statistical model; Data modeling; Bayesian inference; Bayesian probability","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":[0.0003243466,0.0002068657,0.0002949864,0.0004686215,0.0003236564,0.0002187724,0.000313562,0.00006951409,0.00002496682],"category_scores_gemma":[0.00001205101,0.0001808279,0.0003456095,0.001028546,0.00005136567,0.0002910442,0.000002164649,0.0002094562,0.000004912203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000202983,"about_ca_system_score_gemma":0.00003963723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005124489,"about_ca_topic_score_gemma":0.0003791757,"domain_scores_codex":[0.9985466,0.00005176309,0.0003154053,0.0005577246,0.0002246599,0.0003038616],"domain_scores_gemma":[0.9992331,0.0001369335,0.00008224799,0.0003264155,0.0000851861,0.0001361424],"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":[0.00001109401,0.000191046,0.0003543918,0.00002434223,0.0003611559,0.000004692198,0.0004426762,0.07327027,0.001687012,0.0003559672,0.000005280554,0.923292],"study_design_scores_gemma":[0.00009337863,0.00007170879,0.00006449868,0.00001243757,0.0002138382,0.00001083247,0.0000187454,0.6460889,0.3513776,0.001830341,0.00001866395,0.0001990748],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003698068,0.0001231166,0.9955998,0.0001993864,0.0001034293,0.0001169916,0.00001580839,0.0000880347,0.00005537952],"genre_scores_gemma":[0.9764715,0.0001095611,0.02273766,0.0004958968,0.00001060989,0.00003359472,0.000001433638,0.0000109966,0.0001287782],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9728621,"threshold_uncertainty_score":0.737395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03213946701149374,"score_gpt":0.2976170625537154,"score_spread":0.2654775955422217,"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."}}