{"id":"W2608362693","doi":"10.1109/icpr.2016.7900067","title":"Object figure-ground segmentation using zero-shot learning","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Zero (linguistics); Ground zero; Segmentation; Shot (pellet); Artificial intelligence; Object (grammar); Computer science; Computer vision; Figure–ground; Image segmentation; Physics; Linguistics; Materials science; Epistemology; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00008161848,0.00008901455,0.00007138442,0.00004629721,0.0001857767,0.00006457706,0.0003136854,0.00002735801,0.00005338554],"category_scores_gemma":[0.00001939432,0.00006183783,0.00002987807,0.0002978694,0.00002521667,0.0007206569,0.000118013,0.00006147083,0.0001534184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007555298,"about_ca_system_score_gemma":0.00002129672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009781768,"about_ca_topic_score_gemma":0.000003054758,"domain_scores_codex":[0.9991702,0.00003962098,0.000139245,0.0002950861,0.0001493427,0.0002065243],"domain_scores_gemma":[0.9993959,0.0001500149,0.00007387086,0.000285007,0.00004030694,0.00005488559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004893742,0.00003567814,0.002340667,0.000004719249,0.00001390181,0.000004624882,0.0002362046,0.008397454,0.6794296,0.07753748,0.0007236573,0.2312711],"study_design_scores_gemma":[0.003008662,0.0004482639,0.01507526,0.0001968694,0.00004341093,0.0001819609,0.0001875074,0.4586399,0.3516964,0.121024,0.04730083,0.002196912],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05078956,0.00002004799,0.9457445,0.0004952238,0.00008816044,0.0001234224,2.484397e-7,0.0002627653,0.00247612],"genre_scores_gemma":[0.8171894,0.00001415194,0.1799071,0.0002343335,0.00005586422,0.00001579701,0.000001051102,0.000008711074,0.002573575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7663998,"threshold_uncertainty_score":0.2521673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04637618592664908,"score_gpt":0.308124054166354,"score_spread":0.2617478682397049,"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."}}