{"id":"W3195038451","doi":"10.1109/access.2021.3104526","title":"DRVI: Dual Refinement for Video Interpolation","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Motion interpolation; Computer science; Interpolation (computer graphics); Artificial intelligence; Computer vision; Frame (networking); Frame rate; Haar; Haar wavelet; Discrete wavelet transform; Image scaling; Process (computing); Algorithm; Wavelet; Wavelet transform; Motion (physics); Video processing; Image (mathematics); Video tracking; Image processing; Block-matching algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001303771,0.00009007093,0.0001002575,0.00005674133,0.00009455119,0.0004077155,0.0006554713,0.00002760306,0.00001139388],"category_scores_gemma":[0.0001095808,0.0000903297,0.00003868719,0.0002736271,0.00001815136,0.001496282,0.0002921179,0.00006554569,0.000005959628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003979595,"about_ca_system_score_gemma":0.00008221107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005524955,"about_ca_topic_score_gemma":0.00001061154,"domain_scores_codex":[0.9991419,0.00001940629,0.0001788876,0.0003396436,0.0001445619,0.0001755659],"domain_scores_gemma":[0.9991304,0.00006857506,0.00009415547,0.0004209846,0.0002495403,0.00003635236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004691855,0.0003428411,0.001069429,0.0003165772,0.00005966092,0.0001158153,0.0009348319,0.0001062037,0.3308067,0.04731531,0.07210557,0.5467802],"study_design_scores_gemma":[0.0004376615,0.00007005955,0.0002865344,0.0001097885,0.000009473506,0.00003381316,0.00001303718,0.1361476,0.6879412,0.1364565,0.03815895,0.0003354242],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001137121,0.0001243934,0.99568,0.001224498,0.0004548449,0.0001219816,0.000002307613,0.0003667264,0.0008880856],"genre_scores_gemma":[0.1793084,0.000007511459,0.8187692,0.001429383,0.0001165491,0.00009830834,0.000004553439,0.00001131397,0.000254798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5464448,"threshold_uncertainty_score":0.393161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0466808881038223,"score_gpt":0.3688369905730178,"score_spread":0.3221561024691955,"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."}}