{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001248904,0.00008760935,0.00009427511,0.00006541223,0.0001593838,0.0001752604,0.0002345331,0.0000325575,0.0000167817],"category_scores_gemma":[0.0004089937,0.00008561931,0.00003385463,0.0002567463,0.00002749839,0.0001830736,0.0001939052,0.00008556396,0.00002178046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002513778,"about_ca_system_score_gemma":0.00009859452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002535976,"about_ca_topic_score_gemma":0.000287359,"domain_scores_codex":[0.9992307,0.00004201502,0.0001243926,0.0003159785,0.00009813399,0.0001887453],"domain_scores_gemma":[0.9991065,0.0003263165,0.00004200126,0.000362099,0.00007777604,0.00008530465],"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":[0.000002222789,0.00008793182,0.01330419,0.00005126325,0.00002434511,0.00001901844,0.001836241,0.001946323,0.01107621,0.9172949,0.0002997101,0.0540576],"study_design_scores_gemma":[0.0007215036,0.00005407722,0.06668845,0.00002067042,0.00001395275,0.00004773923,0.0002960705,0.9154826,0.00501488,0.01048972,0.0008517663,0.0003185532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08404253,0.0000801827,0.9076267,0.004462326,0.00003414763,0.0001581349,0.000005054962,0.0001961068,0.003394854],"genre_scores_gemma":[0.6482674,0.00000221735,0.3508747,0.0003634697,0.00007519802,0.00003276546,0.00001456552,0.000006791404,0.0003628696],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9135363,"threshold_uncertainty_score":0.3833654,"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."}}