{"id":"W4312276895","doi":"10.1007/978-3-031-22061-6_23","title":"Motion Segmentation Based on Pixel Distribution Learning on Unseen Videos","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Computer vision; Motion (physics); Optical flow; Pixel; Convolutional neural network; Generalization; Focus (optics); Convolution (computer science); Process (computing); Image segmentation; Pattern recognition (psychology); Artificial neural network; Image (mathematics); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007520975,0.0004167965,0.0002992806,0.0006478602,0.0006475582,0.0003756409,0.001403891,0.0001212684,0.00008836564],"category_scores_gemma":[0.0001196009,0.000406615,0.0001121158,0.0006436691,0.0001931324,0.0006871058,0.0005070689,0.001180024,0.00005323987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000891236,"about_ca_system_score_gemma":0.0002059679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006828523,"about_ca_topic_score_gemma":0.00000299119,"domain_scores_codex":[0.9962972,0.00009607899,0.0003832658,0.001404506,0.001352123,0.0004668291],"domain_scores_gemma":[0.9981297,0.0004829102,0.0003206349,0.0008213714,0.0001230942,0.0001222605],"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":[0.000008859125,0.00002137044,0.00002040529,0.000007329797,0.000001422765,0.00001408703,0.00008552539,0.4052841,0.0001708198,0.005126827,0.000008848497,0.5892504],"study_design_scores_gemma":[0.0003389682,0.0004607182,0.0001585605,0.0002062045,0.000003527899,0.000008746853,2.584907e-7,0.9769962,0.001029874,0.01317829,0.007188519,0.0004300943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000344356,0.00003130587,0.9951192,0.001002886,0.001238382,0.0003492895,0.000008909451,0.0002350109,0.001980601],"genre_scores_gemma":[0.4782122,0.00005378881,0.5092036,0.01031782,0.000652962,0.00005957091,0.000366935,0.0001073364,0.001025738],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5888203,"threshold_uncertainty_score":0.9998386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01388521591251851,"score_gpt":0.2636747001939259,"score_spread":0.2497894842814073,"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."}}