{"id":"W2611619280","doi":"10.1117/12.2263190","title":"Deep learning for anomaly detection in maritime vessels using AIS-cued camera imagery","year":2017,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Infrared Target Detection Methodologies","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"AUG Signals (Canada)","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Anomaly detection; Artificial neural network; Computer vision; Deep neural networks; Automatic Identification System; Pattern recognition (psychology); Real-time computing","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":[0.0004506052,0.0006028553,0.0003428423,0.0007120207,0.0002227568,0.0005048679,0.0006213182,0.0004930456,0.001106482],"category_scores_gemma":[0.001277328,0.0002677806,0.000429644,0.0005996365,0.0002696169,0.0008034135,0.0005906346,0.0009228425,0.000313351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007359511,"about_ca_system_score_gemma":0.0007949265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009475186,"about_ca_topic_score_gemma":0.01368459,"domain_scores_codex":[0.9998155,0.00002687122,0.000007441367,0.00004890429,0.00005654136,0.00004481697],"domain_scores_gemma":[0.999689,0.0001159189,0.00003758122,0.00003829778,0.00009569302,0.00002359476],"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":[0.0002850488,0.0002127954,0.004066875,0.00008966358,0.0001016156,0.0001200716,0.00009064889,0.4624493,0.03618162,0.002709394,0.001848753,0.4918443],"study_design_scores_gemma":[0.00000223181,0.00002327237,0.0005714459,0.000003392553,0.000005627334,0.00001120745,0.00001009152,0.9926512,0.005794819,0.0006651309,0.0002581396,0.000003524839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2171904,0.0005691242,0.7772189,0.0002826036,0.00006462829,0.00006504821,0.0002495113,0.002056888,0.002302846],"genre_scores_gemma":[0.8392484,0.0002767432,0.1566871,0.00006988161,0.0000266836,0.00003151199,0.0003494272,0.00006005025,0.00325016],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009475186,"threshold_uncertainty_score":0.01884001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02161033746096815,"score_gpt":0.2597047828865565,"score_spread":0.2380944454255883,"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."}}