{"id":"W2979796099","doi":"10.1109/cvpr.2019.00543","title":"DeepFlux for Skeletons in the Wild","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Vector Institute; University of Toronto","funders":"","keywords":"Skeletonization; Artificial intelligence; Computer science; Computer vision; Pixel; Object detection; Context (archaeology); Benchmark (surveying); Pattern recognition (psychology); Image segmentation; Segmentation; Clutter; Edge detection; Point (geometry); Object (grammar); Representation (politics); Image (mathematics); Image processing; Mathematics; Cartography; Geography","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":[0.0005849584,0.001724535,0.001133695,0.001420614,0.0006197672,0.001283882,0.002950894,0.001470164,0.01144558],"category_scores_gemma":[0.001299305,0.0006819268,0.00100293,0.0009591065,0.0007052087,0.00296837,0.001615348,0.001775548,0.003614268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001392256,"about_ca_system_score_gemma":0.001174934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01351407,"about_ca_topic_score_gemma":0.02334899,"domain_scores_codex":[0.9997248,0.00001902599,0.0000112744,0.0001197164,0.00007023491,0.00005489398],"domain_scores_gemma":[0.9997242,0.00005599014,0.00003097272,0.00009825826,0.00006531923,0.00002520191],"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":[0.0003690158,0.0001961406,0.002330444,0.0002623848,0.0001278989,0.0002849529,0.00007875432,0.1848953,0.01904168,0.01850644,0.04953493,0.724372],"study_design_scores_gemma":[0.00001803209,0.0000434045,0.0004467709,0.00001959357,0.00001239501,0.00007370571,0.00001646299,0.9793753,0.004813625,0.01046966,0.004703346,0.000007574692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06647835,0.001787309,0.8782138,0.0007315583,0.000384453,0.0001814654,0.004098047,0.03939293,0.008732034],"genre_scores_gemma":[0.409832,0.001001838,0.5499457,0.0006096333,0.0001544701,0.0002657786,0.01419408,0.001737784,0.02225875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01351407,"threshold_uncertainty_score":0.03828931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01574845461490725,"score_gpt":0.2728151932646241,"score_spread":0.2570667386497168,"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."}}