{"id":"W2042202438","doi":"10.1117/12.382974","title":"<title>Object-based postprocessing of block motion fields for video applications</title>","year":2000,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Artificial intelligence; Computer vision; Motion estimation; Computer science; Histogram; Motion vector; Segmentation; Pixel; Block (permutation group theory); Template matching; Pattern recognition (psychology); Quarter-pixel motion; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000502875,0.0007713829,0.0007395408,0.001464312,0.0003099872,0.001411422,0.0009980933,0.0009251992,0.06777897],"category_scores_gemma":[0.0007231057,0.0002027427,0.0004268666,0.001480161,0.0003149354,0.001176949,0.0005331013,0.0006368003,0.03456453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005491043,"about_ca_system_score_gemma":0.000496205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002434039,"about_ca_topic_score_gemma":0.002423827,"domain_scores_codex":[0.9997254,0.00003703601,0.00002473583,0.00005510471,0.0001287392,0.00002895245],"domain_scores_gemma":[0.9992983,0.0001135985,0.00004785033,0.0001085385,0.0003864909,0.00004513189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003905479,0.00008016163,0.0004073624,0.0005851658,0.0000354732,0.0002623788,0.0000581414,0.004024796,0.09234913,0.0103292,0.1072035,0.7842742],"study_design_scores_gemma":[0.00006568955,0.0006285071,0.005171973,0.0002053549,0.00005840705,0.0007895675,0.00007775255,0.1541114,0.1593031,0.006873473,0.67261,0.0001047903],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.02164889,0.01534962,0.8236655,0.002239314,0.01311989,0.0009532978,0.00254579,0.01168256,0.1087951],"genre_scores_gemma":[0.1238405,0.01383536,0.3848717,0.001221254,0.004707606,0.0004507813,0.009959972,0.003359674,0.4577533],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9322211,"threshold_uncertainty_score":0.2267433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008855064466572353,"score_gpt":0.2405908226025113,"score_spread":0.231735758135939,"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."}}