{"id":"W2146022472","doi":"10.1007/s11263-006-8614-1","title":"Semantic Modeling of Natural Scenes for Content-Based Image Retrieval","year":2006,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":388,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Image retrieval; Semantic similarity; Categorization; Artificial intelligence; Ranking (information retrieval); Explicit semantic analysis; Information retrieval; Representation (politics); Rank (graph theory); Content-based image retrieval; Similarity (geometry); Visual Word; Pattern recognition (psychology); Image (mathematics); Automatic image annotation; Semantic computing; Mathematics; Semantic technology; Semantic 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003563109,0.0004942893,0.0006468161,0.001594078,0.0003275334,0.0009567929,0.0009028582,0.0006862921,0.001831856],"category_scores_gemma":[0.0009709274,0.0002725493,0.001164404,0.001462746,0.0004080017,0.001718858,0.0004277982,0.0005059866,0.0006231329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007082957,"about_ca_system_score_gemma":0.0007202001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006760044,"about_ca_topic_score_gemma":0.01049688,"domain_scores_codex":[0.9997341,0.00006411814,0.00001740785,0.00006045539,0.0000880858,0.00003588188],"domain_scores_gemma":[0.9997903,0.00005583605,0.0000235037,0.00004515208,0.00007175798,0.00001360646],"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":[0.00069724,0.0006039641,0.002884169,0.0008447667,0.0002546862,0.0005064669,0.000419642,0.3308608,0.1525615,0.07226824,0.01298201,0.4251164],"study_design_scores_gemma":[0.00001399781,0.000060787,0.0007824349,0.00001906781,0.00004696911,0.0001564573,0.00008208449,0.9655423,0.008537139,0.02064706,0.004095139,0.00001654506],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02907398,0.0006444228,0.9663303,0.0001789461,0.00006605271,0.0001332235,0.0007910553,0.00106589,0.001716156],"genre_scores_gemma":[0.6186045,0.001465223,0.3734426,0.0001476656,0.0001059648,0.0002672066,0.003207861,0.0002970437,0.002461842],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006760044,"threshold_uncertainty_score":0.01344138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02323227829819488,"score_gpt":0.2984414559853364,"score_spread":0.2752091776871415,"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."}}