{"id":"W2634948901","doi":"10.1109/ccece.2017.7946736","title":"Improving Right Whale recognition by fine-tuning alignment and using wide localization network","year":2017,"lang":"en","type":"article","venue":"","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Oceanic and Atmospheric Administration","keywords":"Right whale; Computer science; Artificial intelligence; Whale; Deep learning; Task (project management); Process (computing); Population; Pattern recognition (psychology); Computer vision; Engineering; Fishery","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004871259,0.001575211,0.0008174081,0.001034702,0.0004564277,0.000770953,0.0009474173,0.0009372021,0.004474518],"category_scores_gemma":[0.001214235,0.0002960085,0.0007211572,0.0006213437,0.0003024796,0.001639947,0.001493543,0.0007388006,0.003932582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002764709,"about_ca_system_score_gemma":0.0005021833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007529265,"about_ca_topic_score_gemma":0.0114758,"domain_scores_codex":[0.9995579,0.00004922649,0.00002220929,0.0001725902,0.00007701212,0.0001210908],"domain_scores_gemma":[0.9996908,0.00005305035,0.00002569691,0.00009458916,0.0001099452,0.00002590715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003813985,0.0002402907,0.008231882,0.0001715966,0.0001803813,0.0003621503,0.0000923163,0.04289107,0.07794361,0.00124782,0.02034651,0.8479109],"study_design_scores_gemma":[0.00005335552,0.0002738732,0.008445476,0.00004676365,0.0001660124,0.0004183702,0.0003202542,0.9012075,0.07245068,0.003190373,0.01336725,0.00006016529],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2918168,0.002366027,0.6603075,0.0007090454,0.001000679,0.0001350795,0.001466536,0.02641772,0.01578066],"genre_scores_gemma":[0.8171794,0.0005608531,0.1573122,0.000551029,0.0001690629,0.0001050746,0.006721994,0.0006898571,0.01671049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007529265,"threshold_uncertainty_score":0.01497084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02256534273710248,"score_gpt":0.2341969685164176,"score_spread":0.2116316257793152,"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."}}