{"id":"W2110671801","doi":"","title":"Incremental Learning for Visual Tracking","year":2004,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":288,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Particle filter; Artificial intelligence; Computer science; Eye tracking; Tracking (education); Video tracking; Computer vision; Subspace topology; Representation (politics); Inference; Active appearance model; Markov chain Monte Carlo; Task (project management); Pattern recognition (psychology); Object (grammar); Kalman filter; Bayesian probability; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006024801,0.00007754237,0.00009637442,0.00005095037,0.0001595192,0.0001360958,0.0002671733,0.00003111475,0.000007511542],"category_scores_gemma":[0.0000867609,0.00006986619,0.00006268961,0.0001554695,0.00001309928,0.0003810593,0.00006809441,0.00008427424,0.00002249643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003467845,"about_ca_system_score_gemma":0.00003802488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002868287,"about_ca_topic_score_gemma":0.00001503786,"domain_scores_codex":[0.9992504,0.00003727084,0.0001285086,0.0002300555,0.0001294586,0.0002243099],"domain_scores_gemma":[0.999646,0.0001107616,0.00003787804,0.000119978,0.00004215568,0.00004324652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000152148,0.0001393504,0.01133062,0.00002683637,0.00003713056,0.00001406682,0.0009488062,0.005802914,0.02044513,0.1645513,0.00008248779,0.7966062],"study_design_scores_gemma":[0.009673377,0.002268277,0.1238059,0.0001526432,0.00002479045,0.0001622625,0.0005722881,0.09233105,0.6130012,0.1231051,0.03289128,0.002011765],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.071942,0.00002616047,0.9252001,0.0003694594,0.0002005749,0.00009459876,1.069792e-7,0.0002496431,0.001917376],"genre_scores_gemma":[0.7349279,0.000002048726,0.2647013,0.0002187083,0.00006340683,0.000008223399,8.891161e-7,0.000005435086,0.00007209822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7945944,"threshold_uncertainty_score":0.2849061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0371558157009693,"score_gpt":0.3422921101543846,"score_spread":0.3051362944534153,"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."}}