{"id":"W2157970046","doi":"10.1109/tce.2009.5174448","title":"An H.264-based scheme for 2D to 3D video conversion","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Consumer Electronics","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer vision; Computer science; Artificial intelligence; Motion estimation; Stereoscopy; 2D to 3D conversion; Depth map; Block-matching algorithm; Quarter-pixel motion; Motion compensation; Computer graphics (images); Video processing; Video tracking; Image (mathematics)","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":[0.0001621985,0.0002046174,0.000181902,0.0002303852,0.0003400985,0.0001110774,0.0005328584,0.0000696674,0.00002882288],"category_scores_gemma":[0.000007227755,0.0002129766,0.0001106339,0.0004529356,0.00002625407,0.0005385457,0.000001068535,0.0002649443,0.00008437653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001590925,"about_ca_system_score_gemma":0.0002419583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003477158,"about_ca_topic_score_gemma":0.000011113,"domain_scores_codex":[0.9984362,0.0000406679,0.0002199884,0.000533113,0.0002333653,0.0005366908],"domain_scores_gemma":[0.9988119,0.000115748,0.00005235988,0.0006453526,0.0001463055,0.000228329],"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":[0.0002139871,0.000490942,0.000004106986,0.00001159204,0.00002412254,0.000003341953,0.0001301109,0.01180606,0.06470918,0.001602732,0.0008129019,0.9201909],"study_design_scores_gemma":[0.001201186,0.001196929,0.00001727292,0.00002718105,0.00001886482,0.000006672214,0.000009436081,0.6668055,0.2711702,0.0004731688,0.05870834,0.0003652609],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002123557,0.0001352687,0.9942726,0.002316372,0.0003206987,0.0004095022,0.000008543958,0.0003447585,0.00006864289],"genre_scores_gemma":[0.7094076,0.00003569074,0.284315,0.006029301,0.00001754939,0.00003794951,0.000002947761,0.00001808423,0.0001358184],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9198257,"threshold_uncertainty_score":0.8684933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01332768280821222,"score_gpt":0.291655325781635,"score_spread":0.2783276429734228,"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."}}