{"id":"W2913283038","doi":"10.1145/3241055","title":"Deep Semantic Mapping for Heterogeneous Multimedia Transfer Learning Using Co-Occurrence Data","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; McMaster University; St. Francis Xavier University","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China-Yunnan Joint Fund","keywords":"Computer science; Transfer of learning; Deep learning; Artificial intelligence; Semantic matching; Feature learning; Representation (politics); Matching (statistics); Domain (mathematical analysis); Feature (linguistics); Subspace topology; Bridge (graph theory); Natural language processing; Mathematics","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006321822,0.0002998274,0.0003269284,0.0003178158,0.001590708,0.0002890475,0.003571219,0.0001284728,0.00002320524],"category_scores_gemma":[0.00007334523,0.000336227,0.0001122519,0.0006581841,0.0001910434,0.0004675907,0.0002249327,0.0006248527,0.00008485648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006029768,"about_ca_system_score_gemma":0.0001017002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003176207,"about_ca_topic_score_gemma":0.00001583223,"domain_scores_codex":[0.997629,0.0002152687,0.0005856554,0.000863843,0.0002637855,0.0004424672],"domain_scores_gemma":[0.9929552,0.002386603,0.0001699345,0.004102406,0.0001853846,0.0002004875],"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":[0.00001051064,0.0003780242,0.0004636502,0.00008459881,0.0001162461,4.958176e-7,0.003034553,0.08835173,0.002723863,0.0009918376,0.00001095867,0.9038335],"study_design_scores_gemma":[0.0008185804,0.00005502228,0.0001576364,0.00006477333,0.00003978199,0.00002318713,0.0004405002,0.9734936,0.0001466373,0.0001677156,0.02423202,0.0003605667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003911401,0.0003081171,0.9929624,0.0006674664,0.0001370808,0.001433556,0.00009025422,0.0003827051,0.0001069989],"genre_scores_gemma":[0.5480239,0.0002315907,0.4510466,0.0001422594,0.00003255905,0.0001231606,0.0003435654,0.00002332482,0.00003312848],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.903473,"threshold_uncertainty_score":0.999909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0813685521780696,"score_gpt":0.3331669746437586,"score_spread":0.251798422465689,"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."}}