{"id":"W3171326146","doi":"10.3389/fncel.2021.621252","title":"OptiFlex: Multi-Frame Animal Pose Estimation Combining Deep Learning With Optical Flow","year":2021,"lang":"en","type":"article","venue":"Frontiers in Cellular Neuroscience","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"ZonMw; European Research Council; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Koninklijke Nederlandse Akademie van Wetenschappen","keywords":"Optical flow; Artificial intelligence; Computer science; Frame (networking); Estimation; Deep learning; Pose; Computer vision; Engineering; Image (mathematics); Telecommunications","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":[0.0008071701,0.00193468,0.0008734255,0.001092808,0.0002676895,0.0008008551,0.001825105,0.001079143,0.002319612],"category_scores_gemma":[0.001748448,0.0005026794,0.0007425602,0.0005498886,0.0004429994,0.001405656,0.001463249,0.00129851,0.0008839049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008942203,"about_ca_system_score_gemma":0.001109381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008573135,"about_ca_topic_score_gemma":0.02069819,"domain_scores_codex":[0.9996647,0.00003585264,0.00001138219,0.0001385318,0.00009880189,0.00005075846],"domain_scores_gemma":[0.9995885,0.0001260456,0.00007274692,0.00006876697,0.00009193108,0.00005208794],"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":[0.0003614362,0.0003291539,0.01132992,0.0003091345,0.0003423423,0.0001530769,0.00007408771,0.3036716,0.03390501,0.003012108,0.01611667,0.6303955],"study_design_scores_gemma":[0.00001643203,0.0001161635,0.001986357,0.00002184504,0.00001928945,0.00008270588,0.00001150798,0.9876516,0.006359919,0.001876605,0.001838903,0.00001868678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03872966,0.0006555802,0.9430903,0.0001864797,0.0001599636,0.0001473571,0.001700821,0.01349244,0.001837454],"genre_scores_gemma":[0.3995359,0.0005262662,0.5861194,0.0004518259,0.0001263051,0.0003189154,0.006841478,0.0007528274,0.005327155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008573135,"threshold_uncertainty_score":0.01704651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01289561409822144,"score_gpt":0.2490916900753292,"score_spread":0.2361960759771078,"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."}}