{"id":"W2112167252","doi":"10.1109/cccrv.2004.1301449","title":"Improving CBIR systems by integrating semantic features","year":2004,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Relevance feedback; Information retrieval; Semantic gap; Image retrieval; Metadata; Relevance (law); Content-based image retrieval; Process (computing); Semantics (computer science); Automatic image annotation; Artificial intelligence; Image (mathematics); World Wide Web","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":[0.0001731414,0.00009548553,0.00009651206,0.0000482729,0.0001056228,0.0003576143,0.0005026472,0.00005082875,0.000002847617],"category_scores_gemma":[0.0000435219,0.00006940848,0.00003619397,0.0002559201,0.00002236189,0.0003919011,0.00009027517,0.0001163796,0.00003047858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006020971,"about_ca_system_score_gemma":0.00004633892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005402681,"about_ca_topic_score_gemma":0.000004736843,"domain_scores_codex":[0.9992263,0.00002075195,0.0001622528,0.0002402247,0.0001793233,0.0001711246],"domain_scores_gemma":[0.9994736,0.00002414548,0.00007254492,0.0003073649,0.00007334189,0.00004905552],"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":[0.000001501435,0.00006471569,0.00004926089,0.00006800022,0.00001021044,0.000007558998,0.0003550996,0.000006187017,0.289468,0.6039683,0.003849434,0.1021517],"study_design_scores_gemma":[0.0003085967,0.0001285886,0.000174681,0.0001095928,0.00000583218,0.00008491246,0.0003584165,0.0262937,0.9635,0.004592702,0.0040143,0.000428666],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005341482,0.0003744696,0.9923894,0.0008387882,0.0001494866,0.0001290925,6.678511e-7,0.0007632131,0.004820736],"genre_scores_gemma":[0.943472,0.00001173416,0.05370255,0.0002282706,0.00003597798,0.00001617456,0.000001829107,0.00000683181,0.002524678],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9429378,"threshold_uncertainty_score":0.3448483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007709909708895003,"score_gpt":0.2298836656648979,"score_spread":0.2221737559560029,"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."}}