{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000508116,0.0005468718,0.0004589659,0.0001370855,0.0002442771,0.0002489249,0.0007466509,0.0008762589,0.00005608488],"category_scores_gemma":[0.001888902,0.0006333543,0.0002010868,0.0004461496,0.0003002715,0.00001475193,0.0007756486,0.001076839,0.00007218902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002139139,"about_ca_system_score_gemma":0.000972181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001773907,"about_ca_topic_score_gemma":0.000001159334,"domain_scores_codex":[0.9964154,0.0001979951,0.0005594388,0.001438905,0.0006501296,0.0007380824],"domain_scores_gemma":[0.9974286,0.00006472853,0.0003037048,0.0009745992,0.0004860665,0.0007422929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001265115,0.0001378977,0.00008674051,0.0002169697,0.0001037741,0.000009268863,0.000001993711,0.003119814,0.9956095,0.00003644755,0.0005111656,0.00003993677],"study_design_scores_gemma":[0.000537466,0.0002164076,0.0009576078,0.0001064464,0.00006794091,1.574965e-8,0.00000148764,0.1360318,0.8577608,0.000001896246,0.003728577,0.0005895643],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5297955,0.0007482796,0.4671582,0.0008357551,0.0001915189,0.0008469294,0.0001975088,0.0002087789,0.00001751139],"genre_scores_gemma":[0.9067093,0.000112397,0.09188326,0.0003310608,0.0005158901,0.0002688148,0.00002807468,0.0001485135,0.00000275493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3769138,"threshold_uncertainty_score":0.9996118,"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."}}