{"id":"W2162011993","doi":"10.1109/tip.2008.921985","title":"Robust Global Motion Estimation Oriented to Video Object Segmentation","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Computer vision; Motion estimation; Outlier; Computer science; Quarter-pixel motion; Motion compensation; Segmentation; Block-matching algorithm; Image segmentation; Coding (social sciences); Video tracking; Pattern recognition (psychology); Object (grammar); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001117002,0.000174462,0.0001290483,0.0001812871,0.0007043799,0.0001798985,0.0002315673,0.00003895633,0.00001666063],"category_scores_gemma":[0.00001754872,0.0001802444,0.00005668647,0.001135427,0.00004501244,0.002622352,0.00000369445,0.0001430347,0.0001200843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002438154,"about_ca_system_score_gemma":0.00009034109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001394617,"about_ca_topic_score_gemma":0.000003346139,"domain_scores_codex":[0.9985886,0.00004335576,0.0002705923,0.0004612844,0.0003707277,0.000265407],"domain_scores_gemma":[0.9992997,0.00002321119,0.00009281839,0.0002561561,0.0001984656,0.0001296387],"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":[0.00002079077,0.0001249754,0.00001402472,0.00002241217,0.000004612903,0.00001068407,0.0008230087,0.1141879,0.008032184,0.00002766595,0.00011483,0.8766169],"study_design_scores_gemma":[0.0004867651,0.00007602438,0.0003462867,0.00009255835,0.000009348282,0.0001020384,0.00009235893,0.9238755,0.07444313,0.0001682817,0.00007356701,0.0002341043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003918556,0.00002751773,0.9941618,0.0005443497,0.0003916737,0.0002336517,0.000004701933,0.0004577546,0.0002599635],"genre_scores_gemma":[0.4847361,0.000005563779,0.5147742,0.0003446336,0.00001546152,0.00002514792,0.000001882507,0.000008576083,0.00008841116],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8763828,"threshold_uncertainty_score":0.7350152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02448399621604564,"score_gpt":0.2938254174922161,"score_spread":0.2693414212761704,"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."}}