{"id":"W3111344731","doi":"10.1109/smc42975.2020.9283183","title":"Quantifying the Impact of Complementary Visual and Textual Cues Under Image Captioning","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Closed captioning; Artificial intelligence; Feature (linguistics); Convolutional neural network; Encoder; Sentence; Natural language processing; Representation (politics); Sensory cue; Recurrent neural network; Pattern recognition (psychology); Image (mathematics); Speech recognition; Artificial neural network","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":[0.001348185,0.001390022,0.0005091982,0.0007615203,0.0003464877,0.00123374,0.001042375,0.0009391896,0.003194638],"category_scores_gemma":[0.01387304,0.0003146821,0.0004264391,0.0005414738,0.000766356,0.00278283,0.001452494,0.001086036,0.0007138117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006528809,"about_ca_system_score_gemma":0.0004365557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001308313,"about_ca_topic_score_gemma":0.001416789,"domain_scores_codex":[0.9987229,0.0003179435,0.00007869505,0.0002759058,0.0004594852,0.0001450932],"domain_scores_gemma":[0.9945838,0.003354768,0.0004940865,0.0007287734,0.0006354045,0.0002032956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00256326,0.0006945205,0.004155723,0.001368563,0.0001983484,0.001002354,0.0002935657,0.2760592,0.3996488,0.003470594,0.003633215,0.3069119],"study_design_scores_gemma":[0.00005022632,0.001838352,0.004655903,0.000067913,0.0001455979,0.0006335059,0.0001742636,0.6647426,0.3223524,0.002514658,0.002752407,0.00007217418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.782808,0.001817624,0.197883,0.0004386621,0.0003972514,0.0003872452,0.000912795,0.00481053,0.01054492],"genre_scores_gemma":[0.9338144,0.0004302236,0.06176789,0.0001944711,0.00006506676,0.0001393374,0.001046926,0.0005112077,0.002030317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003194638,"threshold_uncertainty_score":0.01068711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06289478724702684,"score_gpt":0.3833081381672803,"score_spread":0.3204133509202535,"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."}}