{"id":"W2296594867","doi":"10.1109/icip.2015.7351397","title":"A sparse coding method for semi-supervised segmentation with multi-class histogram constraints","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Histogram; Artificial intelligence; Segmentation; Pattern recognition (psychology); Computer science; Image segmentation; Scale-space segmentation; Computer vision; Class (philosophy); Image (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":[0.000442484,0.0001411087,0.0001687361,0.00008074918,0.00007227685,0.0001015246,0.0003235312,0.0000471866,0.000007341221],"category_scores_gemma":[0.00009858751,0.0001100001,0.00004420268,0.0002589838,0.00006531,0.0007051077,0.00007457164,0.00007302946,0.000006771737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001026346,"about_ca_system_score_gemma":0.0001022212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002055269,"about_ca_topic_score_gemma":0.000009797102,"domain_scores_codex":[0.9989784,0.00005143316,0.0001825898,0.0003470788,0.0001992638,0.0002412284],"domain_scores_gemma":[0.9990997,0.0001267108,0.00008169244,0.0002876258,0.0002590776,0.0001451701],"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":[0.0001070437,0.0002139532,0.0003072319,0.00005024441,0.00004752356,0.00002569544,0.001738239,0.000143826,0.0359898,0.02823044,0.004095299,0.9290507],"study_design_scores_gemma":[0.003577788,0.0007794203,0.00002897479,0.00005297129,0.00002421472,0.00006905499,0.000617234,0.5632845,0.4169015,0.003923097,0.01026324,0.0004780429],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001368848,0.00003326923,0.9971074,0.0002825543,0.00007491779,0.0006086422,0.000003767111,0.0005173179,0.001235273],"genre_scores_gemma":[0.03234431,0.000005923577,0.9664298,0.0006011726,0.00002086067,0.00008248768,0.000006648709,0.00001201626,0.0004967814],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9285727,"threshold_uncertainty_score":0.4485674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08435190496585189,"score_gpt":0.3591541573013498,"score_spread":0.2748022523354979,"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."}}