{"id":"W3014891935","doi":"10.1101/2020.04.04.025494","title":"OptiFlex: video-based animal pose estimation using deep learning enhanced by optical flow","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Optical flow; Metric (unit); Context (archaeology); Pose; Machine learning; Computer vision; Range (aeronautics); Animal species; Frame (networking); Key (lock); Pattern recognition (psychology); Image (mathematics); Biology; Engineering","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":[0.0005450925,0.001211076,0.0005164637,0.0008134371,0.000174857,0.0005820378,0.001348112,0.0007524427,0.002747528],"category_scores_gemma":[0.001013258,0.0003107527,0.0004066018,0.0004210819,0.0002954451,0.0007980357,0.0007796703,0.0008622219,0.0008405834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007289755,"about_ca_system_score_gemma":0.0008752479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01401539,"about_ca_topic_score_gemma":0.0203175,"domain_scores_codex":[0.9998041,0.00002010426,0.000006031688,0.00007377253,0.00006564169,0.00003026487],"domain_scores_gemma":[0.9997297,0.00007995983,0.00004186981,0.00003963568,0.0000719282,0.0000368558],"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":[0.0005738504,0.0003341331,0.00780573,0.0002488906,0.0002483157,0.0001781398,0.00006257141,0.371788,0.04258235,0.002045982,0.0235828,0.5505493],"study_design_scores_gemma":[0.00001417383,0.00004681052,0.000846503,0.000008953477,0.00000597391,0.00002713338,0.000005044993,0.9921307,0.005459628,0.0005226269,0.0009232891,0.000009169142],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09995683,0.000878526,0.8560331,0.0003476061,0.0002866708,0.0001945438,0.003498425,0.03549574,0.003308517],"genre_scores_gemma":[0.5449535,0.0003389878,0.4405628,0.0003776115,0.00007824536,0.000233634,0.006245762,0.0005833289,0.006626118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01401539,"threshold_uncertainty_score":0.02786762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01361167897906725,"score_gpt":0.2669451250407825,"score_spread":0.2533334460617153,"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."}}