{"id":"W3195852121","doi":"10.1109/ecbios51820.2021.9510291","title":"Policy and Value Deep RL for Temporal Language-Agnostic Street Image Captioning","year":2021,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Closed captioning; Computer science; Artificial intelligence; Natural language; Image (mathematics); Word (group theory); Natural language processing; Encoder; Linguistics","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":[0.001306604,0.0009495509,0.0008563668,0.0004622866,0.000352998,0.0008431029,0.00148372,0.001259643,0.002785817],"category_scores_gemma":[0.004580143,0.0003876315,0.0005431682,0.0005603277,0.0009314558,0.001638295,0.001047926,0.002034712,0.0008648101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001444042,"about_ca_system_score_gemma":0.001315449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00702785,"about_ca_topic_score_gemma":0.008191028,"domain_scores_codex":[0.9994628,0.0001797952,0.00002203276,0.0001832344,0.00007031199,0.0000818223],"domain_scores_gemma":[0.9990389,0.0005630668,0.00008786243,0.0001104844,0.0001363038,0.00006345688],"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":[0.0003139613,0.0002476131,0.001379695,0.0001733218,0.00007731488,0.0001974988,0.0001819816,0.690503,0.01120508,0.0104649,0.01006547,0.2751901],"study_design_scores_gemma":[0.000008830915,0.0000212245,0.0000629504,0.000005205497,0.000004494451,0.0000116384,0.00000929477,0.993681,0.001789188,0.003928429,0.0004726003,0.000005208586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04772808,0.000766208,0.941274,0.0007660235,0.000156976,0.0001236845,0.0004423633,0.004590197,0.004152474],"genre_scores_gemma":[0.8102828,0.0003236998,0.180533,0.0007583603,0.0001196018,0.0002292299,0.00115039,0.0003582087,0.006244685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00702785,"threshold_uncertainty_score":0.01397389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009107360291103987,"score_gpt":0.3028020264338124,"score_spread":0.2936946661427084,"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."}}