{"id":"W2235559271","doi":"10.1007/978-3-319-24261-3_11","title":"Unsupervised Motion Segmentation Using Metric Embedding of Features","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Embedding; Computer vision; Motion (physics); Metric (unit); Image segmentation; A priori and a posteriori; Prior probability; Pattern recognition (psychology)","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":[0.002279063,0.0003798671,0.0005461209,0.001513837,0.0001423257,0.0002683903,0.001741869,0.0002620541,0.000007481618],"category_scores_gemma":[0.000219038,0.0003514492,0.0001241069,0.001408936,0.0002800283,0.0007577681,0.0005981919,0.000472771,0.000004654343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003582395,"about_ca_system_score_gemma":0.000433827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004974583,"about_ca_topic_score_gemma":0.00002060022,"domain_scores_codex":[0.9967526,0.0001066818,0.0005228209,0.00100901,0.00118388,0.0004249611],"domain_scores_gemma":[0.9975926,0.0004423543,0.0004256509,0.0009172856,0.0005013628,0.0001207183],"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":[0.000004744159,0.0000185587,0.0002561848,0.00005363958,0.00001350563,0.00001992765,0.0006588959,0.2262068,0.001529029,0.002739549,0.000005725389,0.7684934],"study_design_scores_gemma":[0.0004542035,0.000156245,0.0008113614,0.0004129721,0.00001868139,0.0000798762,6.351004e-7,0.8814238,0.009786395,0.1061522,0.00007697198,0.0006266874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007221588,0.00107589,0.9955053,0.00008083099,0.001562185,0.0002686335,0.000003869706,0.00009165891,0.0006894163],"genre_scores_gemma":[0.2177532,0.00002390084,0.7817836,0.0001396686,0.0002213762,0.00000192364,0.000005027738,0.00002264953,0.00004871614],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7678667,"threshold_uncertainty_score":0.9998937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05885663374578947,"score_gpt":0.3361807769074182,"score_spread":0.2773241431616287,"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."}}