{"id":"W4320481739","doi":"10.1007/978-3-031-25069-9_15","title":"Distinctive Image Captioning via CLIP Guided Group Optimization","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Closed captioning; Optimal distinctiveness theory; Computer science; Image (mathematics); Artificial intelligence; Metric (unit); Natural language processing; Embedding; Ground truth; Focus (optics); Baseline (sea); Consistency (knowledge bases); Pattern recognition (psychology); Machine learning; 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":[0.0005304999,0.001498502,0.001321094,0.001151,0.0006060549,0.001315564,0.001630977,0.001515093,0.01834494],"category_scores_gemma":[0.001584896,0.0005464517,0.001235913,0.001459049,0.0007430146,0.001307613,0.001920478,0.0019905,0.006410162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004241556,"about_ca_system_score_gemma":0.0005245101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001241469,"about_ca_topic_score_gemma":0.001787714,"domain_scores_codex":[0.999477,0.0001021734,0.00001559318,0.0001508444,0.0001778718,0.00007651599],"domain_scores_gemma":[0.9994104,0.0001823925,0.00003642847,0.0001679798,0.0001449904,0.00005776226],"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":[0.0005357747,0.0001773628,0.000179516,0.0002723818,0.00008788447,0.0002579217,0.0001566467,0.1034166,0.08551177,0.01720122,0.04496774,0.7472351],"study_design_scores_gemma":[0.00003179124,0.0001023982,0.0001415346,0.00001246253,0.00002753121,0.0001543414,0.00004963399,0.9574853,0.02192905,0.01121559,0.00882696,0.00002340674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00645925,0.0001804118,0.984083,0.0001457842,0.0002128932,0.00008624028,0.0001605329,0.00296228,0.005709596],"genre_scores_gemma":[0.1322473,0.0003141339,0.8469424,0.0003525675,0.0003355688,0.0002193905,0.001304649,0.001950321,0.01633372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01834494,"threshold_uncertainty_score":0.06136996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0179301495829788,"score_gpt":0.2746245203832697,"score_spread":0.2566943708002909,"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."}}