{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008457711,0.0001772371,0.0002550655,0.0002391901,0.0001508383,0.0001616439,0.0006791669,0.00005728087,0.00008704117],"category_scores_gemma":[0.00007862644,0.0001664517,0.00003078206,0.000867808,0.0002152081,0.0009277769,0.0001641514,0.0001928342,0.00007669356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001258148,"about_ca_system_score_gemma":0.0002329808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002415053,"about_ca_topic_score_gemma":0.00001897635,"domain_scores_codex":[0.9979725,0.0001039541,0.0005173991,0.0005597055,0.0005005042,0.0003458747],"domain_scores_gemma":[0.998921,0.0000980479,0.000305257,0.0002757582,0.0002992314,0.0001007231],"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":[0.0001418115,0.0003249361,0.0001629406,0.0001440679,0.00001293397,0.00002478918,0.002136469,0.001893019,0.0132302,0.001046954,0.0003566727,0.9805252],"study_design_scores_gemma":[0.00198026,0.0006909205,0.0006211112,0.000847041,0.00002065953,0.00003883014,0.001023096,0.9546759,0.008613379,0.004349478,0.02653207,0.000607217],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005470665,0.001783975,0.9839897,0.0004534928,0.0004090057,0.0001708178,0.000006289404,0.0001068197,0.007609197],"genre_scores_gemma":[0.984537,0.000199572,0.014717,0.0002833821,0.0001318136,0.00000536992,0.00002061801,0.00001478941,0.00009047113],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.979918,"threshold_uncertainty_score":0.6787705,"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."}}