{"id":"W4384789936","doi":"10.1109/tnse.2023.3296511","title":"Delay-Optimized Multi-User VR Streaming via End-Edge Collaborative Neural Frame Interpolation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Windsor; Memorial University of Newfoundland; University of British Columbia","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Interpolation (computer graphics); Frame (networking); Frame rate; Enhanced Data Rates for GSM Evolution; Motion interpolation; Queueing theory; Real-time computing; Virtual reality; Computer vision; Artificial intelligence; Computer network; Video processing; Video tracking","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":[0.0007506377,0.0001711882,0.0001585135,0.000290992,0.0004811492,0.0003606795,0.0003939547,0.00005484713,0.000006125738],"category_scores_gemma":[0.0000164479,0.0001680615,0.00004202108,0.002669772,0.0000928343,0.001349143,0.00001356098,0.0002469416,0.0000178068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008028369,"about_ca_system_score_gemma":0.0001059513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002587296,"about_ca_topic_score_gemma":0.000013466,"domain_scores_codex":[0.9983866,0.00003372625,0.0002248993,0.000420183,0.0004505146,0.0004840821],"domain_scores_gemma":[0.9991849,0.0001670168,0.00004626045,0.0002825636,0.0001803856,0.0001388528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007566844,0.00003048588,0.000009957904,0.00001097576,0.00001545769,0.00001087805,0.00148319,0.9535798,0.006997985,0.0005229122,0.0001021015,0.0372287],"study_design_scores_gemma":[0.0002791235,0.00006419952,0.0004342308,0.00003871021,0.000007292439,0.000007297572,0.0001090216,0.9962353,0.002185017,0.00002494175,0.0004237905,0.000191146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01418,0.00003242459,0.9837571,0.000304689,0.001136336,0.0001718103,0.000003626053,0.0003657654,0.00004828499],"genre_scores_gemma":[0.9212853,0.00004036466,0.07826099,0.0001542228,0.00006567829,0.00003798931,0.000001238207,0.00001141272,0.0001427864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9071053,"threshold_uncertainty_score":0.6853349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01782013628959482,"score_gpt":0.2716729379161933,"score_spread":0.2538528016265985,"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."}}