{"id":"W4405786055","doi":"10.1109/iros58592.2024.10802538","title":"Contextual Emotion Recognition using Large Vision Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Emotion recognition; Human–computer interaction; Speech recognition; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006917989,0.001282752,0.0006984317,0.0006324719,0.0003529948,0.001166477,0.001504769,0.0009255811,0.002067974],"category_scores_gemma":[0.002074016,0.0002997872,0.001396921,0.0003730161,0.0003982146,0.001656785,0.001114452,0.001722809,0.001706071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009559331,"about_ca_system_score_gemma":0.0005849991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00677436,"about_ca_topic_score_gemma":0.009872036,"domain_scores_codex":[0.9994171,0.000128413,0.00002511093,0.0002524639,0.00009225069,0.00008468039],"domain_scores_gemma":[0.9995244,0.0001449008,0.00005116148,0.000102078,0.000138092,0.00003943263],"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":[0.0009849442,0.0008255008,0.004590086,0.0002982434,0.0003151388,0.0004929551,0.000375885,0.1141935,0.07875823,0.008123458,0.03740645,0.7536355],"study_design_scores_gemma":[0.00002997356,0.0001280105,0.001767894,0.00002606762,0.000058592,0.00009242356,0.0001083121,0.974755,0.01115811,0.007490012,0.00435458,0.00003097281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1717522,0.003152811,0.7944605,0.002085014,0.0007213648,0.0002899938,0.002901793,0.01579202,0.008844354],"genre_scores_gemma":[0.7841735,0.0006907695,0.2004482,0.001210045,0.0003202939,0.0002862648,0.005781123,0.0003528063,0.00673697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00677436,"threshold_uncertainty_score":0.01346987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05055027205860438,"score_gpt":0.3150106860660445,"score_spread":0.2644604140074401,"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."}}