{"id":"W2927045701","doi":"10.1007/s10044-019-00812-4","title":"Multi-task non-negative matrix factorization for visual object tracking","year":2019,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"National Natural Science Foundation of China","keywords":"Video tracking; Computer science; Artificial intelligence; Object (grammar); Tracking (education); Subspace topology; Pattern recognition (psychology); Task (project management); Non-negative matrix factorization; Computer vision; Particle filter; Matrix decomposition; Eye tracking; Matrix (chemical analysis); Algorithm; Kalman filter","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":[0.0003045006,0.0001172594,0.0002378814,0.0001906818,0.0001560035,0.0001879873,0.0002426498,0.00004665778,0.000009634552],"category_scores_gemma":[0.00001548892,0.0001065463,0.0001457009,0.0008800569,0.00001539371,0.0002149051,0.00005250673,0.00006168382,0.00002687143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001712642,"about_ca_system_score_gemma":0.00001612868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008882015,"about_ca_topic_score_gemma":0.0000883494,"domain_scores_codex":[0.9990066,0.00004662284,0.0002179714,0.0004390788,0.0001214411,0.0001682496],"domain_scores_gemma":[0.9990991,0.0002522082,0.0001412702,0.0003333244,0.0001192989,0.00005473736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003395414,0.0001718264,0.5397327,0.00006072439,0.0005902168,3.244803e-7,0.0009459166,0.001188645,0.01512702,0.0009398717,0.00001428524,0.4412251],"study_design_scores_gemma":[0.0005164809,0.00004248323,0.482267,0.000008604161,0.0001971764,8.091387e-7,0.00007596208,0.5094522,0.00546159,0.0006986524,0.0009991028,0.0002800035],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02559701,0.00003491855,0.9736537,0.0001113507,0.00003651858,0.0004449467,0.00002319841,0.0000560298,0.00004237831],"genre_scores_gemma":[0.9528219,0.00002048079,0.04665314,0.00009125259,0.00005738023,0.0001862742,0.00004599425,0.000008087532,0.0001154515],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9272249,"threshold_uncertainty_score":0.4344832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02060821318178114,"score_gpt":0.3433326682908139,"score_spread":0.3227244551090328,"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."}}