{"id":"W2891004411","doi":"10.48550/arxiv.1809.03193","title":"Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Object (grammar); Deep neural networks; Pattern recognition (psychology)","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":[0.0002698051,0.0002006726,0.0002311887,0.0002134382,0.00009039304,0.00002709087,0.001549041,0.0001606974,0.000006365068],"category_scores_gemma":[0.00002952064,0.000195548,0.00008795147,0.001420129,0.0002046971,0.0003868421,0.0007200601,0.0006175005,0.000004722882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001985802,"about_ca_system_score_gemma":0.00004027098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002880832,"about_ca_topic_score_gemma":0.001530382,"domain_scores_codex":[0.9983775,0.0002570733,0.0002647672,0.0007105452,0.00009533397,0.0002947588],"domain_scores_gemma":[0.9985304,0.0002558351,0.0002633091,0.0008123479,0.0001001434,0.00003800076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002831835,0.00006095007,0.001990009,0.00001059077,0.000005016883,0.00004737725,0.0001091755,0.9692289,0.00001204651,0.01301602,0.000007946295,0.01548366],"study_design_scores_gemma":[0.0002597326,0.00004356678,0.009872551,0.00002862255,0.000008192606,0.000005080842,0.00003484826,0.9530454,0.00003197307,0.03556445,0.0009194594,0.0001861241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09158538,0.000988576,0.9058763,0.00009039798,0.0003981986,0.0004633431,0.000002642345,0.00005802692,0.0005370962],"genre_scores_gemma":[0.9961522,0.002834545,0.0007774033,0.0001037076,0.0000876823,0.000007176651,0.00001335431,0.0000079699,0.00001601641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9050989,"threshold_uncertainty_score":0.7974216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04409621665771928,"score_gpt":0.2107169426187121,"score_spread":0.1666207259609928,"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."}}