{"id":"W2908757733","doi":"10.1109/ism.2018.00027","title":"Neural Networks Based Fractional Pixel Motion Estimation for HEVC","year":2018,"lang":"en","type":"article","venue":"","topic":"Video Coding and Compression Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Quarter-pixel motion; Motion estimation; Coding (social sciences); Pixel; Data compression; Artificial intelligence; Artificial neural network; Interpolation (computer graphics); Reference software; Computer vision; Reduction (mathematics); Software; Algorithm; Motion (physics); Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002639483,0.0003379524,0.0002343033,0.0004148692,0.0001651749,0.0003018507,0.0003861577,0.000390707,0.001560099],"category_scores_gemma":[0.0007385226,0.000155822,0.0001874786,0.0003530897,0.0001312842,0.0004196527,0.0001780904,0.0003940753,0.0002228082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005254977,"about_ca_system_score_gemma":0.0003622513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01140175,"about_ca_topic_score_gemma":0.0143533,"domain_scores_codex":[0.9998529,0.00002608336,0.000009932744,0.00002838357,0.00006715921,0.0000156751],"domain_scores_gemma":[0.9998183,0.00007255091,0.00002154169,0.00001667413,0.00006532924,0.000005654224],"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":[0.0002690917,0.000079012,0.001235839,0.00007569737,0.00005557625,0.0000781285,0.00002988659,0.3190525,0.053728,0.002596733,0.002054927,0.6207446],"study_design_scores_gemma":[0.000004858436,0.00002356909,0.0007134576,0.000007942187,0.000008807589,0.00002517258,0.000003508954,0.99065,0.00741263,0.0004191026,0.0007230748,0.000007849501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08370032,0.001941663,0.9085494,0.0002731767,0.00012324,0.00006425741,0.0001608177,0.00126275,0.003924408],"genre_scores_gemma":[0.7341153,0.0009368219,0.257327,0.0001260358,0.00005795638,0.00006860687,0.0003008977,0.0000631244,0.007004302],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01140175,"threshold_uncertainty_score":0.02267075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02946517604352763,"score_gpt":0.2798170660793999,"score_spread":0.2503518900358723,"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."}}