{"id":"W3015882298","doi":"10.36227/techrxiv.12093564.v1","title":"Image Captioning with Complementary Visual and Textual Cues","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Closed captioning; Modality (human–computer interaction); Image (mathematics); Computer science; Artificial intelligence; Computer vision; Natural language processing","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":[0.0008312141,0.001619379,0.0008993992,0.001302154,0.0005587499,0.002264914,0.001104203,0.002007748,0.02615845],"category_scores_gemma":[0.005603916,0.0004683754,0.001125511,0.001300043,0.000658941,0.003096398,0.002222274,0.001753294,0.00763208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004273181,"about_ca_system_score_gemma":0.000396055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007611735,"about_ca_topic_score_gemma":0.0009422259,"domain_scores_codex":[0.9992034,0.0002372369,0.00005112676,0.000200445,0.0002217819,0.0000860953],"domain_scores_gemma":[0.9977012,0.0007729089,0.000130859,0.0005237695,0.0007346746,0.0001366401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001550013,0.0002519721,0.000319395,0.001738952,0.0001298352,0.00112559,0.0003595787,0.02154546,0.2536706,0.01014528,0.07230926,0.636854],"study_design_scores_gemma":[0.000144229,0.0006311253,0.001578142,0.0003121744,0.0002750501,0.0020492,0.0004802026,0.5442512,0.3465311,0.02212746,0.08142152,0.0001987133],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03141645,0.002733247,0.9160948,0.001570215,0.002144487,0.0004870423,0.002629034,0.01147922,0.03144547],"genre_scores_gemma":[0.3479089,0.003050033,0.6019964,0.001520835,0.002083045,0.0006875116,0.007673557,0.002621518,0.03245812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02615845,"threshold_uncertainty_score":0.08750874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02176257880009659,"score_gpt":0.3139547987481517,"score_spread":0.2921922199480552,"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."}}