{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001117692,0.0002198282,0.0002144076,0.00007131163,0.0001677376,0.0004112928,0.0006600063,0.00005591208,0.00006121109],"category_scores_gemma":[0.00001305646,0.0001888291,0.00003170756,0.0001221121,0.00008041718,0.0001488381,0.002321122,0.0005606436,0.00005373506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003254283,"about_ca_system_score_gemma":0.00007961778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00348636,"about_ca_topic_score_gemma":0.0001254755,"domain_scores_codex":[0.9985793,0.00006339364,0.0001989701,0.0007332021,0.0002389261,0.0001861913],"domain_scores_gemma":[0.9991822,0.00008186635,0.0001212113,0.0004325621,0.00005172135,0.0001304285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000992336,0.0008020638,0.1657783,0.001270497,0.0009867328,0.0001879535,0.01740479,0.009815985,0.0137699,0.5433076,0.0134782,0.2330987],"study_design_scores_gemma":[0.0003502672,0.0001171339,0.08009116,0.00005337533,0.00002259739,0.0000221269,0.000156083,0.914686,0.0001362769,0.003090351,0.0008380583,0.0004365963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05343059,0.00003023227,0.9317727,0.00934495,0.00003693227,0.0003595135,0.00001303117,0.0005456431,0.004466428],"genre_scores_gemma":[0.569492,0.000003736258,0.4299028,0.0004065463,0.00005881862,0.00004200422,0.00006002423,0.00001059017,0.00002345064],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.90487,"threshold_uncertainty_score":0.7700229,"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."}}