{"id":"W2148049896","doi":"10.1109/tcsvt.2002.806811","title":"Object-based video coding by global-to-local motion segmentation","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Artificial intelligence; Computer vision; Segmentation; Computer science; Coding (social sciences); Image segmentation; Motion estimation; Scale-space segmentation; Coding tree unit; Data compression; Pattern recognition (psychology); Mathematics; Algorithm; Decoding methods","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":[0.0001616557,0.0001908348,0.0002433449,0.0003487754,0.0003732789,0.0001264783,0.0002976607,0.0001377137,0.000007013968],"category_scores_gemma":[0.00001279795,0.0001915434,0.00006487756,0.0007330912,0.00007055396,0.000348694,0.000003048322,0.0001467731,0.0000315473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001839319,"about_ca_system_score_gemma":0.00001472446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002777978,"about_ca_topic_score_gemma":0.000009226856,"domain_scores_codex":[0.9985315,0.00004033973,0.0003386505,0.0005479617,0.0001985699,0.0003430468],"domain_scores_gemma":[0.9992239,0.00008782341,0.00009961558,0.0003741287,0.0001015221,0.0001130071],"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":[0.000005904208,0.0001224565,0.00003006499,0.0000644498,0.00002250778,0.000003528775,0.00009903165,0.006396116,0.02098876,0.00292023,0.001323381,0.9680236],"study_design_scores_gemma":[0.001552895,0.0005557233,0.00001717999,0.0001631242,0.00002341758,0.00008962755,0.0003123363,0.9377865,0.05123043,0.0006913174,0.007164317,0.0004131717],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001764512,0.0003306124,0.9945242,0.001199403,0.0008131732,0.0006758871,0.0000516015,0.0005428991,0.00009775866],"genre_scores_gemma":[0.9950407,0.00003227693,0.004093684,0.0004618152,0.00001446967,0.0002370626,0.000001773745,0.00001440773,0.0001037924],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9932762,"threshold_uncertainty_score":0.7810911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02113973582649241,"score_gpt":0.2653542794674226,"score_spread":0.2442145436409301,"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."}}