{"id":"W4406160139","doi":"10.1016/j.eswa.2025.126416","title":"Inter-frame residual frequency-based reconstruction learning for deep video frame interpolation detection","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Agriculture","funders":"Guangdong Provincial Key Laboratory of Robotics and Intelligent Systems; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Frame (networking); Residual; Artificial intelligence; Residual frame; Computer vision; Interpolation (computer graphics); Deep learning; Motion interpolation; Pattern recognition (psychology); Reference frame; Algorithm; Video tracking; Video processing; Telecommunications; Block-matching algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007202692,0.000738752,0.0007737133,0.0008844104,0.0002216276,0.0004624801,0.001042489,0.0008754886,0.003057774],"category_scores_gemma":[0.00179623,0.0002706061,0.000522894,0.0007137062,0.0002621328,0.0007049788,0.0007640946,0.001186565,0.001325888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003843062,"about_ca_system_score_gemma":0.001004962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005701748,"about_ca_topic_score_gemma":0.008534516,"domain_scores_codex":[0.9996945,0.00004478095,0.00001600654,0.00007635738,0.0001081791,0.00006026792],"domain_scores_gemma":[0.999524,0.0001370091,0.00004535318,0.00007771896,0.000186561,0.00002929037],"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":[0.0003813122,0.0001568728,0.001128012,0.00009347885,0.00005013564,0.00006501983,0.00004828897,0.04786661,0.03752641,0.003384561,0.003578645,0.9057207],"study_design_scores_gemma":[0.000008575184,0.00007190192,0.0004829825,0.00001540314,0.00001779351,0.00005710057,0.0000119991,0.9827679,0.01404061,0.001369628,0.001146983,0.000009036716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01797052,0.0004161976,0.9796292,0.0001041953,0.00005351516,0.00003405607,0.0001129271,0.0008768647,0.0008025572],"genre_scores_gemma":[0.3770093,0.0008378047,0.6139194,0.0002289539,0.00009171898,0.00009282431,0.0009589461,0.0001816892,0.006679384],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005701748,"threshold_uncertainty_score":0.0113371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008576228013502676,"score_gpt":0.2788852912507866,"score_spread":0.2703090632372839,"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."}}