{"id":"W4364322545","doi":"10.1109/tai.2023.3266183","title":"Visual Relationship Detection for Workplace Safety Applications","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Bayesian network; Context (archaeology); Object detection; Visualization; Artificial neural network; Artificial intelligence; Object (grammar); Graphical user interface; Machine learning; Data mining; Pattern recognition (psychology); Programming language","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005360469,0.0001977104,0.0001540704,0.0004451168,0.00113065,0.0001647662,0.0006087538,0.00013679,0.00002861123],"category_scores_gemma":[0.00005879093,0.0002217317,0.0001584483,0.002467598,0.00008078507,0.0003016026,0.000005549959,0.0003997457,0.002153392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001281947,"about_ca_system_score_gemma":0.00006701315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008157046,"about_ca_topic_score_gemma":0.00013195,"domain_scores_codex":[0.9981189,0.00009377291,0.000494517,0.00063819,0.0002760807,0.0003785731],"domain_scores_gemma":[0.9975764,0.001371101,0.0001192886,0.0006370079,0.0001606144,0.0001355695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004815648,0.0001757023,0.00001282659,0.00001470852,0.00001555166,4.515549e-7,0.0003345325,0.2108081,0.0028621,0.05518027,0.00002573276,0.7305219],"study_design_scores_gemma":[0.00004986516,0.0001189177,0.0005328475,0.00001436206,0.00001715766,0.000004204498,0.00009615291,0.8986674,0.05831725,0.03942723,0.002470477,0.0002841679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002064075,0.000005914244,0.992886,0.001752146,0.0004968441,0.001139803,0.00002324134,0.001364704,0.0002672703],"genre_scores_gemma":[0.9762117,0.00001215948,0.02110528,0.0001115735,0.0001092969,0.00186185,0.00001014401,0.00002944151,0.0005485544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9741476,"threshold_uncertainty_score":0.9986235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05401277960001292,"score_gpt":0.34603996480937,"score_spread":0.2920271852093571,"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."}}