{"id":"W3085622691","doi":"10.1109/tip.2021.3060803","title":"Affine Transformation-Based Deep Frame Prediction","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Image Processing","topic":"Video Coding and Compression Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Affine transformation; Computer science; Discrete cosine transform; Encoder; Inter frame; Transformation (genetics); Artificial neural network; Luminance; Artificial intelligence; Algorithm; Mean squared error; Frame (networking); Reference frame; Mathematics; Image (mathematics); Telecommunications; Statistics","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002282908,0.0004511197,0.0004081224,0.0005660498,0.0006201007,0.001427107,0.001268137,0.0005176681,0.00005801909],"category_scores_gemma":[0.00001842023,0.00045291,0.0002848613,0.0007031283,0.000110262,0.001062969,0.00001885704,0.001619108,0.00002089961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001700052,"about_ca_system_score_gemma":0.0005037624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001876849,"about_ca_topic_score_gemma":0.00001152667,"domain_scores_codex":[0.9973862,0.00009548228,0.000589765,0.000912959,0.0006099467,0.000405713],"domain_scores_gemma":[0.9981298,0.00009162741,0.0002528964,0.001048853,0.0003731103,0.0001036527],"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":[0.00002014449,0.000360805,0.000001819744,0.0006433045,0.00004126748,0.00001971216,0.00135024,0.1477555,0.00750777,0.00003246974,0.000065861,0.8422011],"study_design_scores_gemma":[0.0003662988,0.00005973118,0.00001230348,0.001030869,0.00004747956,0.00001401912,0.0001931679,0.7803455,0.2164416,0.000923235,0.0001624834,0.0004033221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001537833,0.0004926421,0.9908262,0.002089556,0.001276782,0.0003209083,0.00003160668,0.002804089,0.0006203043],"genre_scores_gemma":[0.850905,0.00008696348,0.1482853,0.0002523639,0.00004933287,0.0002819889,0.00001963928,0.00003400533,0.00008541419],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8493671,"threshold_uncertainty_score":0.9997923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01922953221118374,"score_gpt":0.257720643789598,"score_spread":0.2384911115784143,"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."}}