{"id":"W4391173394","doi":"10.1117/1.jei.33.1.013028","title":"TEG: image theme recognition using text-embedding-guided few-shot adaptation","year":2024,"lang":"en","type":"article","venue":"Journal of Electronic Imaging","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Theme (computing); Image processing; Embedding; Adaptation (eye); Pattern recognition (psychology); Image (mathematics); Optics; Physics","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":[0.0004749036,0.001372481,0.001023752,0.001122897,0.0004146147,0.0007087296,0.002186546,0.001040083,0.004973318],"category_scores_gemma":[0.001403377,0.00027856,0.00107801,0.000870447,0.0004597382,0.001853234,0.001263499,0.001557073,0.004726788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004633245,"about_ca_system_score_gemma":0.0005897782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003466624,"about_ca_topic_score_gemma":0.006565357,"domain_scores_codex":[0.9995987,0.00004081622,0.00001541766,0.0002125494,0.000079223,0.00005340265],"domain_scores_gemma":[0.9995615,0.00006465856,0.0000315672,0.0001772274,0.000117463,0.00004757718],"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":[0.0006313526,0.0003504425,0.001256082,0.0003985802,0.0001838729,0.0003680223,0.0001853239,0.01645781,0.1235732,0.001745149,0.04168424,0.8131658],"study_design_scores_gemma":[0.00008561648,0.0005830672,0.003924246,0.00005114324,0.00014255,0.001105198,0.0002384142,0.8456289,0.1164722,0.007067248,0.02461123,0.00009016904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1025714,0.003158925,0.8417926,0.0005540927,0.001075902,0.0006071154,0.004057333,0.03825248,0.007930146],"genre_scores_gemma":[0.3970147,0.001215983,0.5469445,0.0009575926,0.0004342982,0.0005230737,0.01802234,0.001700706,0.03318684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004973318,"threshold_uncertainty_score":0.01663744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03676406548906194,"score_gpt":0.3436573871034038,"score_spread":0.3068933216143419,"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."}}