{"id":"W2792038613","doi":"10.1007/s11042-018-5837-4","title":"Saliency inspired quality assessment of stereoscopic 3D video","year":2018,"lang":"en","type":"preprint","venue":"Multimedia Tools and Applications","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stereoscopy; Computer science; Subjective video quality; Computer vision; Distortion (music); Quality (philosophy); Artificial intelligence; Metric (unit); Quality assessment; Task (project management); Video quality; Eye tracking; Pipeline (software); Image quality; Engineering; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007641266,0.0003097065,0.0005633979,0.0001210377,0.0001782135,0.0003313319,0.001207337,0.000235436,0.00003665105],"category_scores_gemma":[0.00005660209,0.0002971725,0.0001240649,0.0002368379,0.000233074,0.0003251612,0.001784319,0.0003804292,0.00002222459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000773088,"about_ca_system_score_gemma":0.0004083173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002457082,"about_ca_topic_score_gemma":0.00002508837,"domain_scores_codex":[0.997202,0.0002090473,0.0009096976,0.000896139,0.0004803663,0.0003026965],"domain_scores_gemma":[0.9967493,0.0003750593,0.0006315726,0.001774463,0.0003051813,0.0001644109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000007409486,0.001429598,0.01171394,0.001666065,0.0002404796,0.00000280123,0.002498687,0.00007114358,0.003384718,0.08129,0.001576166,0.896119],"study_design_scores_gemma":[0.002849645,0.0004497549,0.6756476,0.0008037864,0.0002566084,0.000007531571,0.0003450635,0.1861604,0.006798777,0.05113806,0.07289734,0.002645525],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01194748,0.0002656532,0.9813561,0.0009338911,0.0002985298,0.001479952,0.0003031832,0.0001568881,0.003258353],"genre_scores_gemma":[0.3980349,0.0002771693,0.5986196,0.0004104815,0.0003913862,0.001777518,0.0002685308,0.00002377771,0.0001965706],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8934734,"threshold_uncertainty_score":0.999948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08832387640787122,"score_gpt":0.3931971962749602,"score_spread":0.304873319867089,"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."}}