{"id":"W2111100097","doi":"10.1109/tcsvt.2011.2148490","title":"A Joint Approach to Global Motion Estimation and Motion Segmentation From a Coarsely Sampled Motion Vector Field","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Motion estimation; Artificial intelligence; Motion field; Computer vision; Segmentation; Motion vector; Quarter-pixel motion; Computer science; Outlier; Image segmentation; Block-matching algorithm; Field (mathematics); Motion (physics); Mathematics; Video processing; Video tracking; 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":[],"consensus_categories":[],"category_scores_codex":[0.000729837,0.00104366,0.001330634,0.001320431,0.000397845,0.0008451146,0.0009157551,0.0009811134,0.001544748],"category_scores_gemma":[0.001970386,0.0006743104,0.0009431478,0.001157638,0.0006209553,0.001416381,0.001246942,0.001092172,0.0008362708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003754631,"about_ca_system_score_gemma":0.0007961338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00278172,"about_ca_topic_score_gemma":0.004289309,"domain_scores_codex":[0.9993438,0.0001064396,0.00004739493,0.0001992651,0.000252509,0.00005052791],"domain_scores_gemma":[0.999456,0.0001673662,0.00007218037,0.0001444372,0.0001320107,0.00002798544],"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":[0.0001337355,0.00007961089,0.0006667073,0.0001590215,0.0001037021,0.0001038698,0.0001722469,0.1656333,0.1036996,0.01474986,0.001500761,0.7129976],"study_design_scores_gemma":[0.00001286922,0.0001001515,0.0008442387,0.00001409449,0.00003229679,0.0001594585,0.00002365481,0.9701647,0.01550417,0.008547379,0.004562254,0.00003472111],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001093766,0.00007979247,0.9984131,0.00001792492,0.000009289441,0.00001376435,0.000009400717,0.0001994744,0.0001634557],"genre_scores_gemma":[0.06244139,0.0002553182,0.9351322,0.0000560295,0.00006855431,0.00007009896,0.000197758,0.0001456729,0.001632897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00278172,"threshold_uncertainty_score":0.005531132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05125339156265947,"score_gpt":0.2706481190436611,"score_spread":0.2193947274810016,"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."}}