{"id":"W4312864158","doi":"10.1109/icpr56361.2022.9956609","title":"TempNet: Temporal Attention Towards the Detection of Animal Behaviour in Videos","year":2022,"lang":"en","type":"article","venue":"2022 26th International Conference on Pattern Recognition (ICPR)","topic":"Underwater Vehicles and Communication Systems","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ocean Networks Canada Society; University of Victoria","funders":"","keywords":"Computer science; Artificial intelligence; Residual; Encoder; Feature extraction; Focus (optics); Process (computing); Computer vision; Underwater; Pipeline (software); 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004056082,0.0001509717,0.0001562919,0.0002522722,0.0001205812,0.0000610916,0.0004601988,0.00005013814,0.001772851],"category_scores_gemma":[0.00000431791,0.0001435916,0.00009316791,0.0002052611,0.00003111309,0.0001521742,0.0001318066,0.0004185817,0.00005437914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002053843,"about_ca_system_score_gemma":0.00002697869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000499459,"about_ca_topic_score_gemma":0.0003497991,"domain_scores_codex":[0.9984139,0.0001973607,0.0005086165,0.0002082132,0.0005158759,0.0001560583],"domain_scores_gemma":[0.9994074,0.00003031152,0.0001637389,0.0002264334,0.0001385758,0.00003358147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000423107,0.0007489123,0.09930958,0.0001207956,0.0002730321,0.00002853099,0.002423381,0.001145066,0.3074964,0.0003924283,0.0004122872,0.5872265],"study_design_scores_gemma":[0.0049258,0.001929347,0.6071132,0.0005147749,0.00009849453,0.0002024345,0.01524308,0.2526481,0.09898397,0.004211369,0.01242522,0.001704094],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9884403,0.00004525578,0.006323466,0.0008346547,0.0005313615,0.0003417788,0.0002877947,0.00009713069,0.003098205],"genre_scores_gemma":[0.9988807,0.00004640733,0.00002589144,0.0001336479,0.00006743543,0.0003648619,0.0003238464,0.0000248562,0.0001323698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5855224,"threshold_uncertainty_score":0.9991397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.073748308170705,"score_gpt":0.270744309795047,"score_spread":0.196996001624342,"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."}}