{"id":"W2017293771","doi":"10.1145/1015706.1015764","title":"Keyframe-based tracking for rotoscoping and animation","year":2004,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":209,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Computer vision; Artificial intelligence; Tracking (education); Computer graphics (images); Animation; Sequence (biology); Process (computing); Computer graphics; Interpolation (computer graphics); Tracking system; Video tracking; Video processing; 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":[0.0001079674,0.00009765702,0.00008551,0.0001982351,0.0003397817,0.0001172227,0.0002514444,0.00004393345,0.000001557021],"category_scores_gemma":[0.00003611544,0.00009930363,0.00005957116,0.0003512017,0.00003748674,0.0005530139,0.000003767968,0.0001375751,0.000001872935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002381838,"about_ca_system_score_gemma":0.00003768716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005693503,"about_ca_topic_score_gemma":0.00001015007,"domain_scores_codex":[0.9993306,0.00001213757,0.0001368834,0.0002513336,0.0001078396,0.0001611494],"domain_scores_gemma":[0.9993499,0.0001386814,0.00004348375,0.0003483282,0.00006222932,0.00005736684],"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":[0.00004475424,0.0003211839,0.0001285263,0.0001511127,0.0000303201,0.000003131005,0.000996281,0.02929897,0.006532012,0.07242741,0.00002082405,0.8900455],"study_design_scores_gemma":[0.005798212,0.0009135262,0.002477019,0.0008217999,0.00004769612,0.00002899456,0.0001673011,0.5278203,0.09894386,0.3538705,0.008186785,0.0009240063],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002575437,0.00007097325,0.9933522,0.003423899,0.0001345805,0.0002582902,0.000003122249,0.000165935,0.00001559396],"genre_scores_gemma":[0.5470749,0.00004341846,0.4511946,0.001628274,0.000008812262,0.00003789452,0.00000115937,0.000008260745,0.000002672489],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8891215,"threshold_uncertainty_score":0.4049484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03268142561067876,"score_gpt":0.3068045458424614,"score_spread":0.2741231202317826,"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."}}