{"id":"W26529306","doi":"10.1371/journal.pone.0142110","title":"Unsupervised Learning of Characteristic Object Parts from Videos","year":2009,"lang":"en","type":"article","venue":"Machine Vision and Applications","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pascal (unit); Computer science; Artificial intelligence; Object (grammar); Set (abstract data type); Computer vision; Class (philosophy); Pattern recognition (psychology); Method; Cognitive neuroscience of visual object recognition; Image (mathematics); Unsupervised learning; Object model; Object-oriented programming","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008571811,0.00009073487,0.0001396802,0.00006081814,0.0001206413,0.00004968065,0.0002385831,0.00003082289,0.00001598396],"category_scores_gemma":[0.0000290522,0.00007521654,0.00003297438,0.0002526493,0.00002584807,0.000200893,0.00007394567,0.0001088325,0.000009479732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000059053,"about_ca_system_score_gemma":0.00000920645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001901393,"about_ca_topic_score_gemma":5.236427e-7,"domain_scores_codex":[0.9993404,0.00002821965,0.0001854798,0.0002443514,0.0001045296,0.0000970588],"domain_scores_gemma":[0.9994312,0.00007920356,0.00008309929,0.0003032468,0.00004368277,0.00005959469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000004786803,0.00007005255,0.0004792684,0.000004602651,0.000002884804,8.286253e-7,0.00008904751,0.00000458967,0.03839361,0.01344865,0.00007195386,0.9474297],"study_design_scores_gemma":[0.001326721,0.00119474,0.2682781,0.0001775387,0.00004454125,0.00001801675,0.00004684945,0.1686915,0.1585421,0.1336855,0.2670928,0.000901585],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006962747,0.0004170608,0.9909092,0.0005499273,0.000007646745,0.000195072,0.000008102043,0.0001973935,0.0007528472],"genre_scores_gemma":[0.9727736,0.0002648497,0.02650053,0.0002940135,0.00002947636,0.0000209366,0.00002344578,0.000004282696,0.00008891449],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9658108,"threshold_uncertainty_score":0.3067242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008357095303779183,"score_gpt":0.287837491608897,"score_spread":0.2794803963051178,"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."}}