{"id":"W7116933240","doi":"10.1109/etncc66224.2025.11299754","title":"Automatic Image Tagging and Captioning Using Transformer-Based Vision-Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trinity College","funders":"","keywords":"Closed captioning; Transformer; Encoder; Feature extraction; Natural language; Visualization","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007100901,0.0004061431,0.0004127294,0.000566958,0.001068106,0.001069706,0.0007030228,0.0001503829,0.0001884086],"category_scores_gemma":[0.00007419779,0.0004210658,0.0001339304,0.001230121,0.000222542,0.00120051,0.0001824207,0.0005056314,0.0000265242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001712723,"about_ca_system_score_gemma":0.0004303595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003086798,"about_ca_topic_score_gemma":0.00003400815,"domain_scores_codex":[0.99714,0.0002076737,0.0007024109,0.0009678875,0.0003774558,0.0006045633],"domain_scores_gemma":[0.9982206,0.0003926369,0.0001833666,0.0008772869,0.0001312194,0.0001948527],"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":[0.000009970947,0.0002817459,0.0003245069,0.0006940754,0.000080558,0.00001465353,0.006108874,0.3357615,0.05439332,0.05204352,0.00004542939,0.5502419],"study_design_scores_gemma":[0.0008383336,0.00003914992,0.001426085,0.0005873684,0.00007917205,0.00001032742,0.0002560251,0.9927983,0.001527828,0.002022628,0.00002192038,0.0003928251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2493065,0.0003766642,0.7408803,0.00362449,0.0001270141,0.0005443924,0.000004507761,0.0003726422,0.00476351],"genre_scores_gemma":[0.6571648,0.000007190185,0.3419606,0.0006558571,0.00001919163,0.00002474925,0.000003140338,0.00001881573,0.0001457178],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6570369,"threshold_uncertainty_score":0.9999673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01270002409126329,"score_gpt":0.322999772445022,"score_spread":0.3102997483537587,"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."}}