{"id":"W4312717468","doi":"10.1109/cvpr52688.2022.01145","title":"GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Adjacency list; CAD; Adjacency matrix; Graph; Vertex (graph theory); Theoretical computer science; Symbol (formal); Spotting; Raster graphics; Artificial intelligence; Pattern recognition (psychology); Algorithm; Engineering drawing","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":[0.001491928,0.0004654638,0.0005607063,0.0006763001,0.0007311678,0.0006018544,0.0007668111,0.0001588052,0.0004019672],"category_scores_gemma":[0.00002589448,0.0004995126,0.0002237671,0.0007950676,0.00007337367,0.0006648945,0.0004662261,0.0007143771,0.00007364344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001430527,"about_ca_system_score_gemma":0.0001005549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007983344,"about_ca_topic_score_gemma":0.00005332558,"domain_scores_codex":[0.9958876,0.0005517519,0.0008390602,0.001239544,0.000762445,0.000719561],"domain_scores_gemma":[0.9981733,0.0003809273,0.0004057556,0.0004905299,0.0003324994,0.0002169691],"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":[0.00007329542,0.0002963592,0.001803773,0.0001022055,0.00003307408,0.00004803425,0.0006079914,0.00009692123,0.001843733,0.0005535033,0.004365881,0.9901752],"study_design_scores_gemma":[0.007832041,0.006859628,0.02883352,0.002481716,0.0001046134,0.0004873966,0.0006751769,0.8581124,0.004506378,0.08123181,0.00531599,0.003559323],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2696314,0.00004775817,0.7249325,0.001298412,0.001506329,0.001287604,0.0001159673,0.0004934867,0.0006865587],"genre_scores_gemma":[0.9784631,0.000145867,0.01638052,0.003464575,0.000342208,0.0007677558,0.0002599268,0.0000500983,0.00012592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9866159,"threshold_uncertainty_score":0.9997457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03216264739353678,"score_gpt":0.2714501373813544,"score_spread":0.2392874899878177,"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."}}