{"id":"W2783837693","doi":"10.1109/msp.2017.2763441","title":"Recent Advances in Zero-Shot Recognition: Toward Data-Efficient Understanding of Visual Content","year":2018,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Class (philosophy); Pattern recognition (psychology); Shot (pellet); Zero (linguistics); Machine learning; Training set; Set (abstract data type)","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":[0.001876423,0.001476652,0.002320285,0.001717584,0.0004083893,0.002198521,0.003182446,0.001562523,0.002768875],"category_scores_gemma":[0.00689661,0.0006261219,0.001106802,0.002146612,0.001587508,0.006117337,0.002773321,0.003318019,0.002098795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008650648,"about_ca_system_score_gemma":0.0009699131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003419113,"about_ca_topic_score_gemma":0.003010707,"domain_scores_codex":[0.9982947,0.0003647871,0.0001002884,0.0007064478,0.000443792,0.00008998795],"domain_scores_gemma":[0.9964438,0.001767313,0.0001994843,0.0009088886,0.0005319063,0.0001485796],"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":[0.0001710292,0.000179311,0.001096561,0.0007113168,0.0001039815,0.00008107978,0.0002016766,0.02538391,0.01425361,0.01373323,0.009179818,0.9349046],"study_design_scores_gemma":[0.0000215714,0.0002279034,0.002332099,0.0001994878,0.00008755836,0.0005659067,0.0002538592,0.8265184,0.02818476,0.1113939,0.03010502,0.0001095218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009600243,0.01153442,0.9736229,0.000721321,0.0002271305,0.00006073109,0.0003108146,0.001900493,0.002021908],"genre_scores_gemma":[0.2572115,0.0256656,0.7010359,0.001367152,0.001175131,0.0002189915,0.005004738,0.0005764267,0.007744474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003419113,"threshold_uncertainty_score":0.009923637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2166257512042183,"score_gpt":0.3435192117990915,"score_spread":0.1268934605948731,"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."}}