{"id":"W4293868331","doi":"10.1109/crv55824.2022.00015","title":"Semi-supervised Grounding Alignment for Multi-modal Feature Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Phrase; Margin (machine learning); Leverage (statistics); Machine learning; Ground; Sentence; Feature (linguistics); Transformer; Modal; Classifier (UML); Feature learning; Natural language processing; Question answering; Supervised learning; Feature extraction; Pattern recognition (psychology); Artificial neural network; Engineering","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":[0.0003848634,0.0001485416,0.0001412725,0.0001042693,0.001141796,0.0001485135,0.0009705451,0.00003617155,0.0001080713],"category_scores_gemma":[0.00006293591,0.0001504194,0.0001016158,0.0003632868,0.00001426824,0.0001829646,0.0006960433,0.0004374604,0.00002718404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001810583,"about_ca_system_score_gemma":0.0000452288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000182608,"about_ca_topic_score_gemma":0.000004036093,"domain_scores_codex":[0.9985093,0.0001334941,0.0001613651,0.0005243244,0.0003271379,0.000344306],"domain_scores_gemma":[0.9991618,0.000174224,0.0000830682,0.0004439919,0.00004145767,0.00009546176],"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":[0.00004634715,0.0008358521,0.02781205,0.00008928313,0.0001437046,0.00001383193,0.00883314,0.2330648,0.03853832,0.5145453,0.009610729,0.1664666],"study_design_scores_gemma":[0.000688566,0.0000987114,0.006185419,0.000002531805,0.000005471731,0.00001347597,0.0002510905,0.9463905,0.0002169661,0.0003435162,0.04559798,0.0002057935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.030668,0.00004389436,0.9622232,0.004592615,0.0002215887,0.0005603182,0.000004478769,0.0005764044,0.001109527],"genre_scores_gemma":[0.6748187,0.000001243446,0.3199728,0.0004895289,0.000048886,0.0006109164,0.00002284949,0.00001743768,0.00401759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7133257,"threshold_uncertainty_score":0.8781884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03163132250895909,"score_gpt":0.3021625355299601,"score_spread":0.270531213021001,"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."}}