{"id":"W2120486209","doi":"10.1109/tip.2005.863969","title":"Relevance feedback for CBIR: a new approach based on probabilistic feature weighting with positive and negative examples","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Relevance feedback; Weighting; Probabilistic logic; Feature (linguistics); Feature selection; Image retrieval; Data mining; Relevance (law); Artificial intelligence; Pattern recognition (psychology); Context (archaeology); Similarity (geometry); Machine learning; Information retrieval; 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":[0.000156248,0.0002382385,0.0001945938,0.0001406852,0.0005101165,0.0004385539,0.0002365524,0.00007860809,0.000002173809],"category_scores_gemma":[0.00002847121,0.0001895761,0.00005452908,0.0005550213,0.0001427172,0.0007034719,0.000001852012,0.0002539261,0.000002342766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009036664,"about_ca_system_score_gemma":0.0002108412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003294224,"about_ca_topic_score_gemma":0.00000874826,"domain_scores_codex":[0.9986123,0.00004635207,0.0001899854,0.0006253493,0.0002566592,0.0002693788],"domain_scores_gemma":[0.998888,0.0003093812,0.0001500079,0.0002565704,0.0003209729,0.00007508346],"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":[0.0005871044,0.0007727605,0.000006177107,0.000653696,0.00002878522,0.000007811444,0.001165825,0.002757115,0.02373656,0.001756273,0.0004847418,0.9680431],"study_design_scores_gemma":[0.001240718,0.0004363525,0.0001845431,0.0005160861,0.00005223923,0.00003038869,0.0001063356,0.6498001,0.3424444,0.004364849,0.0003342311,0.0004897077],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001980197,0.0000594511,0.9959703,0.001447428,0.00002678496,0.0006577563,0.00001638535,0.000350503,0.001273391],"genre_scores_gemma":[0.3771244,0.000003856521,0.6217071,0.0002096377,0.00003805571,0.0001287196,0.000003604368,0.00002229562,0.0007623431],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9675534,"threshold_uncertainty_score":0.773069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01508547826667142,"score_gpt":0.2412298420891336,"score_spread":0.2261443638224622,"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."}}