{"id":"W3211256241","doi":"10.32920/ryerson.14649465.v1","title":"Combining visual features and contextual information for image retrieval and annotation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Image retrieval; Automatic image annotation; Artificial intelligence; Annotation; Visual Word; Discriminative model; Feature (linguistics); Pattern recognition (psychology); Context (archaeology); Semantic gap; Information retrieval; Visualization; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003681964,0.0001759906,0.0002221148,0.0001298617,0.0001363336,0.001427374,0.0002181146,0.00020872,0.000003131051],"category_scores_gemma":[0.0002365946,0.0001641485,0.00004968407,0.0001276143,0.00007588125,0.001358983,0.0005990468,0.0002436001,9.668589e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002968837,"about_ca_system_score_gemma":0.0001137431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001951534,"about_ca_topic_score_gemma":0.000001823317,"domain_scores_codex":[0.9989615,0.00004679557,0.0003083806,0.0003290287,0.0002073533,0.0001469195],"domain_scores_gemma":[0.998868,0.0001434965,0.0002160421,0.0002269513,0.0004801596,0.00006535504],"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":[0.0003123371,0.0001545647,0.0001651619,0.001770731,0.0001554251,0.000009173747,0.01225818,0.000002222385,0.03554938,0.1917149,0.003803786,0.7541041],"study_design_scores_gemma":[0.003420181,0.0009951596,0.02912566,0.0006217255,0.0001183076,0.000241357,0.00421046,0.2806852,0.6429069,0.02927052,0.006209889,0.002194669],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01165474,0.0003104571,0.9852572,0.001098954,0.0001889943,0.0005310899,0.00001362162,0.0002891501,0.0006557816],"genre_scores_gemma":[0.7090055,0.000365055,0.2887971,0.0008190984,0.00007063313,0.00006984573,0.0003581686,0.00001334666,0.00050134],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7519094,"threshold_uncertainty_score":0.9996092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01501415510110963,"score_gpt":0.2887571363566685,"score_spread":0.2737429812555588,"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."}}