{"id":"W7117239698","doi":"10.1145/3786588","title":"MSDA-Net: Multi-source Domain Adaptive Network for Multi-modal Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Feature (linguistics); Pattern recognition (psychology); Emotion recognition; Feature extraction; Domain (mathematical analysis); Feature learning; Joint (building)","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":[0.0008609918,0.00131727,0.000621362,0.0005841124,0.0002813216,0.0005384196,0.001363426,0.0009952741,0.002328467],"category_scores_gemma":[0.001667605,0.0003087246,0.000771535,0.0004861407,0.0003130441,0.001106647,0.00101344,0.001575688,0.001062557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005080468,"about_ca_system_score_gemma":0.0004105156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002369458,"about_ca_topic_score_gemma":0.005175051,"domain_scores_codex":[0.9997427,0.00006912649,0.00001225141,0.0001053027,0.00004041352,0.0000302314],"domain_scores_gemma":[0.9996741,0.0001245734,0.00003040621,0.00005631339,0.00009209321,0.00002253852],"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":[0.0005649175,0.0004297133,0.002815273,0.0002247727,0.0003356865,0.0001995315,0.0001085922,0.2273158,0.02277872,0.00382835,0.02094392,0.7204547],"study_design_scores_gemma":[0.00001705021,0.00007994142,0.0007365557,0.000009898536,0.00002327011,0.00004691104,0.0000187418,0.9898543,0.003936814,0.003238108,0.002022963,0.00001542245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04602083,0.001415503,0.9424433,0.0004464469,0.0002863019,0.0001336034,0.0008737618,0.005363326,0.003016898],"genre_scores_gemma":[0.6127071,0.0009384748,0.3662476,0.0007212554,0.0001969827,0.0005208534,0.004750101,0.0003685771,0.01354906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002369458,"threshold_uncertainty_score":0.007789433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02492786121120636,"score_gpt":0.3015296854222537,"score_spread":0.2766018242110473,"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."}}