{"id":"W3126271000","doi":"10.1007/s11263-021-01430-6","title":"DeepFlux for Skeleton Detection in the Wild","year":2021,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Vector Institute; Centre for Social Innovation; University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Skeleton (computer programming); Pattern recognition (psychology); Topological skeleton; Representation (politics); Benchmark (surveying); Context (archaeology); Pixel; Computer vision; Clutter; Object detection; Convolutional neural network; Field (mathematics); Segmentation; Mathematics; Active shape model; Geography; Cartography","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":[],"consensus_categories":[],"category_scores_codex":[0.0003203841,0.00007131484,0.00009720867,0.0001216326,0.00005064058,0.0001628285,0.001082641,0.00003016529,0.00000221744],"category_scores_gemma":[0.00003467443,0.00005304149,0.0001067133,0.0002524681,0.00001378894,0.0005220899,0.0001300643,0.0001616679,0.000003937103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000632068,"about_ca_system_score_gemma":0.00004454113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.665554e-7,"about_ca_topic_score_gemma":0.000008917089,"domain_scores_codex":[0.9989222,0.00007231376,0.0003515065,0.0001469854,0.0004028728,0.0001041492],"domain_scores_gemma":[0.9986451,0.0003735812,0.00022563,0.0001915908,0.0005347381,0.00002938232],"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":[0.00003492479,0.0001566183,0.00007566538,0.000002829148,0.00002377055,0.00009715203,0.000267843,0.01018273,0.004170317,0.01698322,0.001653479,0.9663514],"study_design_scores_gemma":[0.002321482,0.0006850676,0.01437304,0.0001880172,0.00001272688,0.002995278,0.00004062522,0.6885266,0.02157984,0.09534907,0.1736498,0.0002783944],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02622723,0.00009460483,0.9646929,0.007572175,0.001263503,0.00008506227,7.004866e-7,0.00001105846,0.00005278208],"genre_scores_gemma":[0.8572457,0.000042621,0.1405426,0.001402091,0.0007401049,0.000006253233,0.000001887482,0.000004743664,0.00001392008],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.966073,"threshold_uncertainty_score":0.2162969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01378964007880394,"score_gpt":0.3143395868782434,"score_spread":0.3005499467994395,"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."}}