{"id":"W1579900930","doi":"10.1007/11676959_9","title":"A Generative Model of Dense Optical Flow in Layers","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Generative model; Representation (politics); Optical flow; Interpolation (computer graphics); Inference; Generative grammar; Probabilistic logic; Flow (mathematics); Frame (networking); Algorithm; Inverse; Artificial intelligence; Motion (physics); Motion interpolation; Inverse problem; Computer vision; Image (mathematics); Mathematics; Geometry; Object (grammar); Mathematical analysis; Block-matching algorithm","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004782542,0.0003867612,0.0005349871,0.0008454857,0.00008599608,0.0001572042,0.001881973,0.0001861547,0.000004646336],"category_scores_gemma":[0.00007276794,0.0003520881,0.0001091203,0.0005380503,0.0006082649,0.0005708007,0.0009457099,0.0006519192,0.000008413514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002291934,"about_ca_system_score_gemma":0.0004703525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001317402,"about_ca_topic_score_gemma":0.00005787683,"domain_scores_codex":[0.9969612,0.00002340484,0.0005723253,0.001151467,0.0007675477,0.0005240459],"domain_scores_gemma":[0.9983835,0.0002445752,0.0001982765,0.0008693766,0.0001901828,0.0001141012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003134725,0.00001956816,0.00001208817,0.000009242021,0.00000160058,0.00003660149,0.0002851209,0.6657587,0.0005998602,0.006916298,0.00001367053,0.3263441],"study_design_scores_gemma":[0.000237366,0.00005300704,0.00002062213,0.0002467009,0.000001868771,0.00001580701,9.314473e-8,0.8895254,0.004915376,0.1046099,0.00004579302,0.0003280236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009059534,0.0002836233,0.9952185,0.0004655672,0.0003992375,0.0002125472,0.000003681833,0.0000533837,0.003272837],"genre_scores_gemma":[0.07885386,0.00002147484,0.9199197,0.0008897474,0.00008858698,0.000003796238,0.000001531782,0.00001884988,0.0002024131],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3260161,"threshold_uncertainty_score":0.9998931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02043482809651988,"score_gpt":0.2647887230120216,"score_spread":0.2443538949155017,"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."}}