{"id":"W4362007666","doi":"10.47611/jsrhs.v11i3.2957","title":"Lucas-Kanade Optical Flow Machine Learning Implementations","year":2022,"lang":"en","type":"article","venue":"Journal of Student Research","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"McGill University","keywords":"Optical flow; Pixel; Computer vision; Flow (mathematics); Ground truth; Computer science; Artificial intelligence; Motion blur; Frame (networking); Computation; Set (abstract data type); Sequence (biology); Ambiguity; Motion (physics); Image (mathematics); RADIUS; Implementation; Algorithm; Mathematics; Geometry; Telecommunications","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002798949,0.00006245561,0.0001288581,0.0004282597,0.0008854583,0.0002088693,0.001192847,0.000008195548,0.0004269074],"category_scores_gemma":[0.0001326607,0.00005346504,0.00007552789,0.000680604,0.00003887818,0.0004042709,0.001436571,0.001331143,0.00001521611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002680682,"about_ca_system_score_gemma":0.0001869785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001017151,"about_ca_topic_score_gemma":0.00000394912,"domain_scores_codex":[0.9967009,0.0003734419,0.0003500109,0.0001506205,0.002067362,0.0003576487],"domain_scores_gemma":[0.9989625,0.0002806595,0.0001066615,0.0001747997,0.0003072429,0.0001680914],"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":[0.00009726793,0.001386438,0.05412231,0.00002357766,0.0001930791,0.001851461,0.01202078,0.03288238,0.01333442,0.03149509,0.02125877,0.8313344],"study_design_scores_gemma":[0.004430482,0.004032916,0.06887584,0.00005736641,0.00002014199,0.001663563,0.01490867,0.4597507,0.00180426,0.00648104,0.4374912,0.0004838098],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07300038,0.001438785,0.8910656,0.02836729,0.0009556442,0.0003461731,0.000004682875,0.00005248132,0.004768973],"genre_scores_gemma":[0.9035245,0.0001257502,0.09508535,0.000221912,0.0001419367,0.00001017543,0.000001364774,0.00001006274,0.0008789463],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8308506,"threshold_uncertainty_score":0.6810318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1714916004945291,"score_gpt":0.5146902562661904,"score_spread":0.3431986557716613,"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."}}