{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001039117,0.0005387054,0.0004606159,0.0008979336,0.0005670371,0.0007346213,0.003116718,0.000296629,0.00003184566],"category_scores_gemma":[0.0002878526,0.0005437454,0.0001365111,0.001189557,0.0005968287,0.0007374127,0.001695659,0.001033965,0.0002606613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004431255,"about_ca_system_score_gemma":0.0002417405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002665897,"about_ca_topic_score_gemma":0.00006982936,"domain_scores_codex":[0.9957835,0.00006582428,0.000629845,0.001906202,0.0009659451,0.0006486561],"domain_scores_gemma":[0.9967095,0.0006857305,0.0004553082,0.001589698,0.0003722367,0.0001875356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002161095,0.00002090802,0.00008030792,0.00002151022,0.000009644907,0.00002779427,0.0004296533,0.7851023,0.0001848407,0.02329138,0.00001670211,0.1908128],"study_design_scores_gemma":[0.0001843106,0.00006041199,0.0009307068,0.0001513552,0.000008242938,0.00003641735,1.000111e-7,0.9242316,0.00007242405,0.07368872,0.0001066559,0.0005290293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003161411,0.00003332972,0.9927144,0.001140081,0.001113257,0.0005616924,0.000007014993,0.0007625709,0.003636053],"genre_scores_gemma":[0.06173897,0.00001456044,0.9367412,0.0004972134,0.0004526252,0.00005043996,0.00004592254,0.00007439424,0.0003846966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1902837,"threshold_uncertainty_score":0.9997014,"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."}}