{"id":"W2130864343","doi":"10.1109/tbc.2010.2043896","title":"Motion-Compensated Frame Rate Up-Conversion—Part I: Fast Multi-Frame Motion Estimation","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Broadcasting","topic":"Video Coding and Compression Technologies","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"Communications Research Centre Canada","funders":"","keywords":"Motion estimation; Quarter-pixel motion; Motion interpolation; Block-matching algorithm; Computer science; Computer vision; Motion compensation; Motion field; Interpolation (computer graphics); Maximum a posteriori estimation; Frame (networking); Frame rate; Artificial intelligence; Motion (physics); Inter frame; Reference frame; Algorithm; Mathematics; Video processing; Telecommunications; Video tracking; Statistics","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":[0.0004592306,0.0006415613,0.0005871486,0.0009226776,0.0002642582,0.0005312499,0.0005967814,0.0005887359,0.004505597],"category_scores_gemma":[0.001305619,0.00029735,0.0003629539,0.0006122277,0.0001984792,0.0007876956,0.0002969636,0.0004808066,0.001666214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000319217,"about_ca_system_score_gemma":0.0003957536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001991833,"about_ca_topic_score_gemma":0.002097445,"domain_scores_codex":[0.9996998,0.00004113227,0.00001614814,0.00005683755,0.0001609583,0.00002496552],"domain_scores_gemma":[0.9996412,0.000123482,0.00004791785,0.00007442195,0.0001020009,0.00001096162],"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":[0.0002607925,0.0000741437,0.0008109224,0.0002008604,0.00003894276,0.00011677,0.00005704792,0.02331144,0.1378058,0.003743227,0.003301659,0.8302785],"study_design_scores_gemma":[0.00005090358,0.0003227391,0.007506898,0.00007656304,0.00005234093,0.001099544,0.00004028126,0.6335768,0.3233992,0.002719283,0.03105931,0.00009626806],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01951936,0.0008838503,0.9754024,0.00005993168,0.0000648343,0.00009796514,0.000121107,0.001402105,0.002448427],"genre_scores_gemma":[0.2195508,0.0009609985,0.7712152,0.00005214541,0.00006584911,0.0001213449,0.0005297216,0.000180984,0.007322897],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004505597,"threshold_uncertainty_score":0.01507276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03051193962009272,"score_gpt":0.2595124744239057,"score_spread":0.229000534803813,"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."}}