{"id":"W2104246590","doi":"10.1109/iccv.2003.1238464","title":"Entropy-of-likelihood feature selection for image correspondence","year":2003,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Pattern recognition (psychology); Entropy (arrow of time); Artificial intelligence; Feature selection; Feature (linguistics); Markov random field; Mathematics; Ambiguity; Computer science; Bayesian information criterion; Image (mathematics); Image segmentation","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":[0.0002363654,0.00007305398,0.00008813924,0.0000649974,0.00006323515,0.00005515074,0.0002874236,0.0000525354,0.00004109829],"category_scores_gemma":[0.0001462864,0.00006009582,0.0000593743,0.000390842,0.00002489013,0.0003181403,0.00002030781,0.00005966041,0.00001570917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002449147,"about_ca_system_score_gemma":0.00007949294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002976749,"about_ca_topic_score_gemma":9.006573e-7,"domain_scores_codex":[0.9993455,0.0000383681,0.0001194429,0.0002022743,0.0001394784,0.000154974],"domain_scores_gemma":[0.9993701,0.00007043921,0.00007464226,0.0002080483,0.0002376027,0.00003914533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001161981,0.00005945108,0.0001695851,0.00001849903,0.000005406965,3.479765e-7,0.00005485996,1.459106e-7,0.3008732,0.6733133,0.009321562,0.01617197],"study_design_scores_gemma":[0.0001452769,0.0001085062,0.0001856087,0.000005708092,0.000003204359,0.00001289086,0.00001138456,0.006156818,0.9408998,0.02009712,0.03228466,0.00008901448],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003804901,0.00004620437,0.9951864,0.0004835086,0.0001191887,0.0002107313,0.000001303284,0.0002055614,0.00336658],"genre_scores_gemma":[0.2263948,0.00002072223,0.7656707,0.0001975344,0.00002196354,0.00004219534,0.000001681846,0.000007080058,0.007643355],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6532162,"threshold_uncertainty_score":0.2450636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01175084329196912,"score_gpt":0.2659059869863825,"score_spread":0.2541551436944133,"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."}}