{"id":"W3134680050","doi":"10.1109/tmm.2021.3052419","title":"Video Frame Interpolation via Generalized Deformable Convolution","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Motion interpolation; Computer science; Interpolation (computer graphics); Artificial intelligence; Kernel (algebra); Computer vision; Frame (networking); Optical flow; Convolution (computer science); Motion estimation; Algorithm; Motion (physics); Mathematics; Video tracking; Video processing; Block-matching algorithm; Image (mathematics); Artificial neural network","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":[0.0001036588,0.0001485406,0.0001521267,0.000140732,0.0002145431,0.00009363025,0.0002336972,0.00007447826,0.0002276735],"category_scores_gemma":[0.00001320697,0.0001489074,0.0001103587,0.0004187562,0.00003877385,0.0009737079,0.00000423782,0.0002619666,0.0003557826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000864937,"about_ca_system_score_gemma":0.00007026373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002993032,"about_ca_topic_score_gemma":0.00002091167,"domain_scores_codex":[0.9987929,0.00007500332,0.0002586091,0.0003657273,0.0002452195,0.0002625425],"domain_scores_gemma":[0.9991288,0.00009402259,0.00006374016,0.0004385192,0.0001487861,0.000126175],"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":[0.00003964353,0.0002971799,0.00003489601,0.00001537824,0.00004512555,0.0000252887,0.001307946,0.02017885,0.170172,0.0003235874,0.0004585681,0.8071015],"study_design_scores_gemma":[0.0006923688,0.00002959131,0.00009760388,0.00002621143,0.000007981657,0.00002792119,0.00002856271,0.8925385,0.1035528,0.0005333406,0.002304286,0.0001608171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001944322,0.00007963932,0.9949894,0.0005614249,0.001695684,0.0001115733,0.000005319379,0.000268221,0.0003444401],"genre_scores_gemma":[0.5952859,0.00005613427,0.4029947,0.0008219446,0.00004534056,0.00002269391,0.000006495379,0.00001323924,0.0007535506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8723597,"threshold_uncertainty_score":0.6072268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01515195106255921,"score_gpt":0.2686879798880343,"score_spread":0.253536028825475,"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."}}