{"id":"W4387951185","doi":"10.1109/ccece58730.2023.10288687","title":"An Investigation of Latency-Accuracy Trade-off in Inter-frame Video Prediction using Quantized CNNs","year":2023,"lang":"en","type":"article","venue":"","topic":"Video Coding and Compression Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Codec; Convolutional neural network; Latency (audio); Floating point; Coding (social sciences); Artificial intelligence; Motion estimation; Frame rate; Integer (computer science); Inter frame; Frame (networking); Real-time computing; Algorithm; Computer vision; Reference frame; Mathematics; Computer hardware; Computer network; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003690518,0.0001061704,0.0001701069,0.0004603065,0.00006181258,0.00007182551,0.0007003357,0.0001109054,0.000006051353],"category_scores_gemma":[0.0001462928,0.00009259139,0.00004115979,0.001281808,0.00006199006,0.0008460697,0.0001975167,0.0001549211,0.000007987402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002998941,"about_ca_system_score_gemma":0.00005185145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001705389,"about_ca_topic_score_gemma":0.0000193434,"domain_scores_codex":[0.9988192,0.0000947095,0.0003741215,0.0003174134,0.0001979767,0.0001965581],"domain_scores_gemma":[0.9991457,0.0001245273,0.0001289436,0.0005247134,0.00003225046,0.00004388326],"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":[0.00002347474,0.0001267626,0.07514789,0.00007836064,0.00002193514,0.00001872143,0.005364723,0.007420623,0.727724,0.03003465,0.001262334,0.1527766],"study_design_scores_gemma":[0.0002729929,0.0001135781,0.02548508,0.000140242,0.000002640688,0.000004264797,0.0003198028,0.856493,0.1002079,0.01680229,0.00004591531,0.000112321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8849125,0.00002376913,0.1124167,0.0009926014,0.0002398411,0.0001090586,0.000001682569,0.001258798,0.0000451101],"genre_scores_gemma":[0.9816695,0.00004248833,0.01818143,0.0000573733,0.00001260395,0.000004588072,0.00000390343,0.000006512027,0.00002153644],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8490724,"threshold_uncertainty_score":0.3775767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0558933028965484,"score_gpt":0.3044283889960401,"score_spread":0.2485350860994917,"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."}}