{"id":"W3133424709","doi":"10.1109/iros45743.2020.9340905","title":"Understanding Contexts Inside Robot and Human Manipulation Tasks through Vision-Language Model and Ontology System in Video Streams","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Ontology; Robot; Scheme (mathematics); Artificial intelligence; Human–computer interaction; Process (computing); Object (grammar); Mobile robot; Computer vision","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":[0.0001178811,0.0001192256,0.0001805711,0.00005879027,0.0001438628,0.0001125985,0.0001869403,0.00006768615,0.000002821145],"category_scores_gemma":[0.0000246575,0.0001124561,0.00001435529,0.0001649459,0.00004076984,0.0003630404,0.0002050481,0.0001573027,0.000004202498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009083236,"about_ca_system_score_gemma":0.00001466539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002345641,"about_ca_topic_score_gemma":0.001040081,"domain_scores_codex":[0.9989966,0.00007063019,0.0002309376,0.0004304659,0.0001140821,0.0001573096],"domain_scores_gemma":[0.9995011,0.0001011031,0.00007784319,0.0002260948,0.00001491407,0.00007893006],"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":[0.000006081794,0.00002281087,0.01078722,0.00006243111,0.00000848484,0.00001227517,0.00809801,0.04540907,0.003539584,0.9282712,0.00003182586,0.003751007],"study_design_scores_gemma":[0.0004813262,0.0000507312,0.02417615,0.00002998581,0.000003699748,0.00001147924,0.0005768954,0.97043,0.00004197952,0.004075607,0.000004409387,0.0001177944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2710848,0.0000687061,0.7247258,0.001759552,0.00001121261,0.0001979107,8.388003e-7,0.0001581046,0.001993086],"genre_scores_gemma":[0.9678757,0.000002482449,0.03169222,0.0003782718,0.00001381342,0.00001293293,0.000004510605,0.000008551046,0.00001146887],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9250209,"threshold_uncertainty_score":0.4585828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08615830094156307,"score_gpt":0.3290150866216928,"score_spread":0.2428567856801297,"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."}}