{"id":"W2963513598","doi":"10.1109/cvpr.2016.323","title":"Learning Structured Inference Neural Networks with Label Relations","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":127,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Categorization; Abstraction; Artificial intelligence; Exploit; Semantics (computer science); Inference; Benchmark (surveying); Set (abstract data type); Encoding (memory); Multi-label classification; Machine learning; Image (mathematics); Artificial neural network; Pattern recognition (psychology); Contextual image classification; Deep learning","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":[0.00006143733,0.0000926577,0.00008127664,0.00004279692,0.0001160536,0.00006677365,0.0003280362,0.00003966977,0.00003860604],"category_scores_gemma":[0.00008824215,0.00004866086,0.00001525983,0.0002995566,0.00004514972,0.000944076,0.0001231911,0.0001355017,0.0000109473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001886452,"about_ca_system_score_gemma":0.00001891747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004463446,"about_ca_topic_score_gemma":0.000006549951,"domain_scores_codex":[0.9993225,0.00003205309,0.0001045333,0.000225851,0.000121216,0.0001938791],"domain_scores_gemma":[0.9993752,0.0001590513,0.00005502178,0.000268103,0.00008650499,0.0000561704],"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":[0.00001268359,0.00001339294,0.01557852,0.00000158935,0.000009501406,0.00001286382,0.000088448,0.001504793,0.001834312,0.0640725,0.0003174224,0.916554],"study_design_scores_gemma":[0.002140193,0.001987523,0.03702322,0.0001659575,0.00001858674,0.00009355137,0.00003883609,0.8633492,0.03531693,0.04671977,0.01186091,0.001285322],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003288914,0.00003123092,0.9935976,0.0005677525,0.00003609363,0.00007453135,2.007877e-7,0.0006192254,0.001784442],"genre_scores_gemma":[0.8228143,0.00001706281,0.1749667,0.000132756,0.00002238125,0.000004728834,4.185551e-7,0.000005583177,0.002036094],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9152687,"threshold_uncertainty_score":0.1984332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01460195490070895,"score_gpt":0.2736443086600053,"score_spread":0.2590423537592964,"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."}}