{"id":"W4360765155","doi":"10.1109/icmla55696.2022.00154","title":"Recurrent Neural Network-Based Video Compression","year":2022,"lang":"en","type":"article","venue":"","topic":"Video Coding and Compression Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Encoder; Data compression; Video quality; Artificial intelligence; Peak signal-to-noise ratio; Video compression picture types; Video tracking; Multiview Video Coding; Quantization (signal processing); Computer vision; Compression ratio; Recurrent neural network; Artificial neural network; Real-time computing; Video processing; 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":[0.000229839,0.00012031,0.0001323282,0.0000941808,0.0006239417,0.00009848383,0.001691922,0.00002822211,0.0002003906],"category_scores_gemma":[0.00001868375,0.00009911487,0.00007462717,0.000512054,0.00002727645,0.0001371703,0.001745698,0.0003201465,0.00001807563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000414049,"about_ca_system_score_gemma":0.00003710229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001044674,"about_ca_topic_score_gemma":9.737208e-7,"domain_scores_codex":[0.9985845,0.0001441278,0.000186096,0.0003774315,0.0003938382,0.0003139903],"domain_scores_gemma":[0.9989978,0.0001078061,0.00008152112,0.0007299216,0.00002724419,0.00005567474],"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":[0.00002157468,0.00016386,0.001467387,0.000007696388,0.000007059702,0.00002956589,0.0000611997,0.1548962,0.000579703,0.04490487,0.2568045,0.5410565],"study_design_scores_gemma":[0.0003256483,0.0002142177,0.0005758579,0.00001451933,0.00000202885,0.0000105692,0.0000274631,0.9087375,0.001926693,0.004958672,0.08299444,0.0002124371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04573121,0.001247756,0.9206871,0.01522375,0.004088746,0.000374792,0.000003856055,0.005960298,0.006682545],"genre_scores_gemma":[0.9808875,0.000004007933,0.01729972,0.001280086,0.00003614859,0.00008707066,0.000002782604,0.000006370748,0.0003963127],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9351563,"threshold_uncertainty_score":0.4798918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0277157249118717,"score_gpt":0.2517377682174916,"score_spread":0.2240220433056198,"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."}}