{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001709484,0.00007030765,0.0000590362,0.0001547688,0.00006942431,0.0003370073,0.0002314759,0.00006191192,0.00007900133],"category_scores_gemma":[0.00001384932,0.00005788483,0.00003759166,0.0003048085,0.0000159029,0.00146641,0.0001178846,0.00007873953,0.0002309412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004153967,"about_ca_system_score_gemma":0.00002056397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001668904,"about_ca_topic_score_gemma":0.000004295762,"domain_scores_codex":[0.9993242,0.00002063694,0.000125931,0.0002520256,0.0001390128,0.0001381769],"domain_scores_gemma":[0.9996592,0.00003104456,0.00002187461,0.0002341042,0.00003137827,0.00002240205],"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":[0.000001406204,0.00003747232,0.000005144399,0.00001649217,0.000007222848,0.000009583199,0.0009529263,0.00003191422,0.009121182,0.3874817,0.001953723,0.6003813],"study_design_scores_gemma":[0.0001008612,0.00003137244,0.00002749302,0.00004108413,0.000003311734,0.000008399551,0.0005801488,0.9446103,0.007978682,0.04526237,0.00125066,0.0001053415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0516114,0.0003253694,0.9409696,0.0008528754,0.0002560023,0.00008612812,0.000003566612,0.001768875,0.004126125],"genre_scores_gemma":[0.968309,0.00001912551,0.03094287,0.0001135808,0.0000268521,0.000004546646,0.0000102542,0.000005235581,0.0005685608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9445783,"threshold_uncertainty_score":0.3249769,"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."}}