{"id":"W2139047213","doi":"10.1007/s11263-007-0075-7","title":"Incremental Learning for Robust Visual Tracking","year":2007,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":3101,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Honda Research Institute, USA","keywords":"Computer science; Artificial intelligence; Tracking (education); Subspace topology; Computer vision; Representation (politics); Active appearance model; Principal component analysis; Pattern recognition (psychology); Eye tracking; Forgetting; Video tracking; Range (aeronautics); Object (grammar); Image (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002009888,0.001089748,0.002090422,0.001386688,0.0005269422,0.0009994226,0.003131081,0.001729646,0.002884089],"category_scores_gemma":[0.008665325,0.001146382,0.001085995,0.0013851,0.0009305462,0.002189225,0.002189293,0.002139969,0.001023263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008211816,"about_ca_system_score_gemma":0.0008910609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005057028,"about_ca_topic_score_gemma":0.004592802,"domain_scores_codex":[0.9990742,0.0001994113,0.00005990475,0.0002981055,0.000269358,0.00009889952],"domain_scores_gemma":[0.9965886,0.001960199,0.0002299241,0.0006077072,0.0005226413,0.00009097088],"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":[0.0004693058,0.0001601702,0.0008459025,0.0001869823,0.0001395362,0.0001024162,0.00008593845,0.2559152,0.01108361,0.01253382,0.004523092,0.713954],"study_design_scores_gemma":[0.00001354849,0.00003749294,0.0001710601,0.000005226413,0.00001500115,0.00002871694,0.000003635942,0.9924098,0.001962796,0.004823727,0.000521088,0.000007923154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006183305,0.0003102176,0.9923286,0.00005210376,0.00004790055,0.00002342265,0.00003325095,0.0006684705,0.0003527816],"genre_scores_gemma":[0.377993,0.0005842917,0.6147482,0.0002404251,0.0001818559,0.0002574642,0.0005907684,0.0004252536,0.00497865],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005057028,"threshold_uncertainty_score":0.01062942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03210245907793505,"score_gpt":0.3744627854844399,"score_spread":0.3423603264065048,"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."}}