{"id":"W4404820294","doi":"10.1007/978-3-031-72848-8_26","title":"CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre for Social Innovation","funders":"","keywords":"Closed captioning; Computer science; Image (mathematics); Natural language processing; Artificial intelligence; Information retrieval","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":[0.0005721565,0.002134628,0.001236585,0.001027242,0.0005049194,0.001672399,0.002265958,0.001407163,0.02914339],"category_scores_gemma":[0.001706388,0.0007826903,0.00145964,0.001229904,0.0007916986,0.002099475,0.002875094,0.00193902,0.0159008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003892579,"about_ca_system_score_gemma":0.0006882397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001896147,"about_ca_topic_score_gemma":0.002808561,"domain_scores_codex":[0.99935,0.0001011459,0.00003477337,0.0001973323,0.0002541575,0.0000625957],"domain_scores_gemma":[0.9992223,0.0002241848,0.00003231223,0.0003061523,0.0001624202,0.0000526421],"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":[0.0007418647,0.0002329573,0.0001575806,0.0007941755,0.0001047115,0.0004179134,0.000163539,0.01833299,0.1384195,0.02122399,0.1080566,0.7113543],"study_design_scores_gemma":[0.0001473761,0.0002961248,0.0004843298,0.0001063813,0.00008722439,0.0007441643,0.00008784531,0.6878115,0.1617818,0.04806953,0.1002589,0.0001246504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004112376,0.0005060121,0.9330472,0.0001059721,0.0004370887,0.00023172,0.001722723,0.0479023,0.01193459],"genre_scores_gemma":[0.07848524,0.000451992,0.8942213,0.0003009327,0.0002387252,0.000441712,0.007736523,0.005757827,0.01236569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02914339,"threshold_uncertainty_score":0.09749436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008056717923322488,"score_gpt":0.2529892578538221,"score_spread":0.2449325399304996,"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."}}