{"id":"W2116091511","doi":"10.1109/tce.2011.5955224","title":"A high performance hardware architecture for multi-frame hierarchical motion estimation","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Consumer Electronics","topic":"Video Coding and Compression Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Communications Research Centre Canada","funders":"","keywords":"Motion estimation; Computer science; Block-matching algorithm; Frame rate; Quarter-pixel motion; Chrominance; Computer vision; Pixel; Frame (networking); Artificial intelligence; Block (permutation group theory); Interpolation (computer graphics); Motion compensation; Reference frame; Lookup table; Metric (unit); Luminance; Computer hardware; Motion (physics); Mathematics; Video processing; Engineering; Telecommunications","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":[0.0001421327,0.0002210656,0.0001958886,0.0002527063,0.0003929464,0.00006732556,0.0006831326,0.0001833646,0.00001432453],"category_scores_gemma":[0.00001601867,0.0002009952,0.0001143144,0.0003238923,0.00008348603,0.0002757487,0.000005733079,0.0006042792,0.00003354891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008673708,"about_ca_system_score_gemma":0.0001075259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001393412,"about_ca_topic_score_gemma":0.00001999062,"domain_scores_codex":[0.9985768,0.00004981405,0.0002509189,0.0004638341,0.0002039838,0.0004546493],"domain_scores_gemma":[0.9990385,0.00009523217,0.00008759336,0.0006095886,0.00009804817,0.00007110373],"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":[0.00007147283,0.000243634,0.000009080167,0.00003112394,0.00004516599,0.00000108266,0.0003224382,0.009218615,0.00099452,0.004611304,0.0000712653,0.9843803],"study_design_scores_gemma":[0.00097659,0.0006401725,0.0001668063,0.00006462181,0.00003917682,0.00003377522,0.00001061017,0.7068331,0.2841882,0.005397542,0.001283221,0.0003662379],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02947503,0.0001444249,0.9682847,0.0003956697,0.0004150645,0.0003574475,0.00001172717,0.0008975593,0.00001834819],"genre_scores_gemma":[0.7601073,0.0001064728,0.2392825,0.0001041774,0.000007549025,0.0002034249,0.000002389153,0.00001581041,0.0001703901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.984014,"threshold_uncertainty_score":0.8196346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0359682742101675,"score_gpt":0.2560472080568123,"score_spread":0.2200789338466448,"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."}}