{"id":"W2608655061","doi":"10.1109/icpr.2016.7899947","title":"Look who is not talking: Assessing engagement levels in panel conversations","year":2016,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Automatic summarization; Nonverbal communication; Computer science; Robustness (evolution); Human–computer interaction; Artificial intelligence; Natural language processing; Psychology; Communication","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":[0.000597318,0.0005314309,0.0003032988,0.0009019098,0.000238632,0.000624907,0.0003025303,0.0006820546,0.001238388],"category_scores_gemma":[0.003148441,0.0001083796,0.0002392494,0.0002520908,0.0002768438,0.0005230166,0.0008653776,0.0002947887,0.0007738221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001432611,"about_ca_system_score_gemma":0.0001463312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007314535,"about_ca_topic_score_gemma":0.001937938,"domain_scores_codex":[0.9994591,0.0001628644,0.0000423191,0.0001532533,0.0001018074,0.00008078657],"domain_scores_gemma":[0.9986995,0.0004822107,0.0002996702,0.00006554492,0.0001787663,0.0002741842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005602038,0.001000251,0.4180641,0.00101426,0.0003840246,0.001264561,0.006618698,0.004365629,0.2590113,0.0004294773,0.002985602,0.29926],"study_design_scores_gemma":[0.00004597315,0.002093409,0.9199109,0.0001518845,0.0001963725,0.00198032,0.007742437,0.03609036,0.02768298,0.001059167,0.002943738,0.0001023969],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9844357,0.0002992098,0.01252494,0.00006189443,0.00002724366,0.00008738349,0.0006246223,0.0001495997,0.001789475],"genre_scores_gemma":[0.9921108,0.000153048,0.005940497,0.00003711421,0.00002452772,0.00007642923,0.0009091716,0.00002050075,0.0007279754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001238388,"threshold_uncertainty_score":0.004142761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1332065229563885,"score_gpt":0.311265917157815,"score_spread":0.1780593942014265,"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."}}