{"id":"W2962740177","doi":"10.1109/tmm.2019.2891418","title":"MC-SSM: Nonparametric Semantic Image Segmentation With the ICM Algorithm","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Image segmentation; Artificial intelligence; Segmentation; Scale-space segmentation; Pattern recognition (psychology); Nonparametric statistics; Algorithm; Computer vision; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001888631,0.0002054084,0.0001756403,0.0002417459,0.0001803185,0.0001397069,0.0005621616,0.00006492846,0.00006604213],"category_scores_gemma":[0.000005487598,0.0001359879,0.00008662573,0.001127408,0.00008583153,0.0009137096,0.00000405345,0.0003474367,0.0005317146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000069263,"about_ca_system_score_gemma":0.00004703044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002818643,"about_ca_topic_score_gemma":0.000006682307,"domain_scores_codex":[0.9986113,0.00007114199,0.0001866843,0.0004182572,0.0004209993,0.0002916573],"domain_scores_gemma":[0.9986956,0.0003425768,0.00009360295,0.0006672022,0.0001195352,0.0000815434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002599219,0.0001695498,0.0000127623,0.00001546855,0.00004008583,0.00001642459,0.0006277476,0.0006928223,0.01378495,0.00001921972,0.0002952465,0.9842997],"study_design_scores_gemma":[0.001185066,0.0006629861,0.0002772725,0.0000473193,0.00004521167,0.00004694119,0.0001465096,0.289428,0.7062785,0.0001774145,0.001275631,0.0004291981],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002323569,0.00003776443,0.9953529,0.0004430057,0.0003612417,0.0008408104,0.00001041101,0.0003752688,0.0002550325],"genre_scores_gemma":[0.3149119,0.0001036922,0.6830055,0.0005301409,0.00004098583,0.0001387925,0.000003106494,0.00002891288,0.001236923],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9838705,"threshold_uncertainty_score":0.6834293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008836781364611048,"score_gpt":0.2599988188402725,"score_spread":0.2511620374756615,"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."}}