{"id":"W1509719082","doi":"10.1109/icassp.1997.595386","title":"Prediction and search techniques for RD-optimized motion estimation in a very low bit rate video coding framework","year":2002,"lang":"en","type":"article","venue":"","topic":"Video Coding and Compression Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Motion estimation; Motion vector; Computer science; Quarter-pixel motion; Motion compensation; Block-matching algorithm; Data compression; Bit rate; Artificial intelligence; Coding tree unit; Rate–distortion optimization; Harmonic Vector Excitation Coding; Computer vision; Coding (social sciences); Rate–distortion theory; Algorithm; Mathematics; Decoding methods; Video tracking; Video processing; Statistics; Real-time computing; Image (mathematics)","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":[0.0004825124,0.0001076247,0.0001427321,0.0003097701,0.0001389576,0.0001942197,0.0002825677,0.0001566424,0.00000973822],"category_scores_gemma":[0.0002879908,0.00009492673,0.00003090081,0.0003880097,0.00003829484,0.0005794044,0.0001606332,0.000182941,0.000004720355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004686398,"about_ca_system_score_gemma":0.000007256688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001239859,"about_ca_topic_score_gemma":7.838752e-7,"domain_scores_codex":[0.9990421,0.00005928286,0.0002185566,0.0003365462,0.0001386408,0.0002048755],"domain_scores_gemma":[0.9992723,0.000287854,0.0000531453,0.000296584,0.00005780183,0.0000323364],"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":[0.00003825562,0.0001290654,0.0005907257,0.0001060589,0.00001166523,0.000004054258,0.0006421923,0.003332932,0.005877269,0.04350494,0.002575652,0.9431872],"study_design_scores_gemma":[0.0002849574,0.00009275381,0.0003910754,0.0002113953,0.000002143953,0.000003859306,0.00002993927,0.9378142,0.03924193,0.02177267,0.00005682792,0.00009820124],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0172037,0.0000775068,0.9789806,0.001894718,0.00009448847,0.0003557502,0.000001352669,0.001198553,0.0001933335],"genre_scores_gemma":[0.6262068,0.0001404195,0.3733746,0.00006910109,0.00001182225,0.0001018595,0.000001104531,0.000004938002,0.00008940956],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.943089,"threshold_uncertainty_score":0.3871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04160567302898525,"score_gpt":0.2753190492159475,"score_spread":0.2337133761869622,"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."}}