{"id":"W2609825896","doi":"10.1109/cvpr.2017.477","title":"Annotating Object Instances with a Polygon-RNN","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":372,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; “la Caixa” Foundation; Nvidia","keywords":"Computer science; Polygon (computer graphics); Segmentation; Artificial intelligence; Annotation; Object (grammar); Generalization; Ground truth; Factor (programming language); Matching (statistics); Process (computing); Pattern recognition (psychology); Image segmentation; Vertex (graph theory); Pixel; Computer vision; Graph; Theoretical computer science; Mathematics; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001182539,0.00009952979,0.0001105702,0.00003841255,0.0004531396,0.0004658246,0.001032683,0.00002291737,0.000006167299],"category_scores_gemma":[0.00008632457,0.00006686088,0.00002472764,0.0000949788,0.00008150064,0.00192326,0.0002281383,0.00008424334,0.00001318321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001300126,"about_ca_system_score_gemma":0.00004277683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007980911,"about_ca_topic_score_gemma":0.00003925076,"domain_scores_codex":[0.9992486,0.00001099687,0.0001005753,0.0002644302,0.0001694529,0.0002059246],"domain_scores_gemma":[0.9989057,0.00003350632,0.0001262055,0.0008154711,0.00007008139,0.00004901361],"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":[0.00002172226,0.0000394452,0.007251092,0.00001649701,0.00001724363,0.0001063462,0.0004710644,0.000002552504,0.003582577,0.08311911,0.0009626191,0.9044097],"study_design_scores_gemma":[0.001292018,0.001268478,0.0357987,0.0003122801,0.00001177346,0.0001323308,0.0002231905,0.007827136,0.8509436,0.05218766,0.04876448,0.001238308],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004563815,0.00009130822,0.9298748,0.0004781872,0.00005304326,0.00008925029,4.566673e-7,0.0003801483,0.06446903],"genre_scores_gemma":[0.6350989,0.00002371137,0.3636575,0.0002380829,0.00002886496,0.000006315714,1.484579e-7,0.000004894612,0.0009416122],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9031714,"threshold_uncertainty_score":0.4491958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01881389897620761,"score_gpt":0.3009481754234627,"score_spread":0.2821342764472551,"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."}}