{"id":"W2085758610","doi":"10.1117/12.2043128","title":"Characterizing perceptual artifacts in compressed video streams","year":2014,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Compression artifact; Lossy compression; Video compression picture types; Data compression; Coding (social sciences); Perception; Multiview Video Coding; Motion compensation; Computer vision; Video processing; Video tracking; Video quality; Artificial intelligence; Real-time computing; Image compression; Image processing","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":[0.001075921,0.000307095,0.0004521637,0.0001335191,0.00008885565,0.0002831281,0.001733993,0.0001533404,0.000008525642],"category_scores_gemma":[0.0004562189,0.0002668464,0.0004329928,0.0003695571,0.0001460362,0.00133004,0.0003816057,0.0003540112,0.000003992895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001494941,"about_ca_system_score_gemma":0.00004016389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001785045,"about_ca_topic_score_gemma":4.292729e-7,"domain_scores_codex":[0.9974306,4.069776e-8,0.0008169123,0.0004973188,0.0007654463,0.0004896487],"domain_scores_gemma":[0.9983054,0.0002226727,0.0003732408,0.0001068052,0.0008600989,0.0001317384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002418658,0.0001440459,0.000294341,0.0002246478,0.000090575,8.415574e-8,0.0009160186,0.00005307231,0.5417125,0.4537159,0.0004991425,0.002325517],"study_design_scores_gemma":[0.002760014,0.0006506432,0.01248946,0.0008742622,0.00009025655,0.00002091257,0.00311978,0.5515542,0.4140464,0.005724087,0.00766116,0.001008783],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9910277,0.00002159287,0.002335558,0.003900606,0.0002402033,0.0003741112,0.000009928062,0.0001039548,0.001986333],"genre_scores_gemma":[0.8162962,0.00001996556,0.1828748,0.000339328,0.0002732131,0.00009014364,0.000005481136,0.00003173133,0.00006909738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5515012,"threshold_uncertainty_score":0.9999784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01741984006576065,"score_gpt":0.251992241212581,"score_spread":0.2345724011468203,"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."}}