{"id":"W2134644497","doi":"10.1109/icme.2010.5583034","title":"Motion segmentation in compressed video using Markov Random Fields","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Artificial intelligence; Markov random field; Maximum a posteriori estimation; Segmentation; Computer science; Pattern recognition (psychology); Markov process; Image segmentation; Computer vision; Prior probability; A priori and a posteriori; Random field; Markov chain; Mathematics; Maximum likelihood; Machine learning; Bayesian probability","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":[0.000145086,0.00005318776,0.00006739665,0.00007831439,0.00004663068,0.00007273289,0.0001775993,0.00002720519,0.00007593217],"category_scores_gemma":[0.0000268495,0.00004725392,0.00001894478,0.0001575517,0.00001112937,0.0006746989,0.00006659824,0.0001226639,0.000009186457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001094406,"about_ca_system_score_gemma":0.000009828628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005004285,"about_ca_topic_score_gemma":0.00003778415,"domain_scores_codex":[0.999476,0.00002665965,0.0001283588,0.0001595442,0.0001013051,0.0001080931],"domain_scores_gemma":[0.9996758,0.00005358233,0.00003346123,0.0001818967,0.00002492811,0.00003030846],"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":[0.00002140932,0.00006676654,0.003498065,0.000008626271,0.00000263008,0.000007208798,0.0004936036,0.002477187,0.4097091,0.003837043,0.0002376818,0.5796407],"study_design_scores_gemma":[0.00108003,0.000005484677,0.002415672,0.000007182582,6.439977e-7,0.000004436014,0.00002114946,0.9708869,0.02382944,0.001501173,0.0001785559,0.00006937623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07212157,0.000005425469,0.9254373,0.0003621727,0.0003599381,0.0000884322,9.583339e-8,0.00005749708,0.001567619],"genre_scores_gemma":[0.6700949,0.000001520841,0.3294409,0.0003654651,0.00001706331,0.000001804166,6.883202e-7,0.000002024466,0.00007563314],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9684097,"threshold_uncertainty_score":0.1926959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01510924514920187,"score_gpt":0.2957855549703238,"score_spread":0.2806763098211219,"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."}}