{"id":"W3193773166","doi":"10.1109/iccv48922.2021.01577","title":"GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Network","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Ground truth; Graph; Pattern recognition (psychology); Theoretical computer science","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":[0.0002626688,0.000445515,0.0003829669,0.0002490898,0.0003241526,0.0006993166,0.001575894,0.0001398526,0.0005897285],"category_scores_gemma":[0.00002499679,0.0004576807,0.0002320119,0.001054579,0.00008380884,0.0006822129,0.0004242723,0.0004423662,0.0006731555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001986669,"about_ca_system_score_gemma":0.0002552499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001029768,"about_ca_topic_score_gemma":0.00003461215,"domain_scores_codex":[0.9961122,0.0002517515,0.0007132774,0.001314068,0.001041374,0.0005673898],"domain_scores_gemma":[0.9970589,0.0003751487,0.0003686816,0.00112363,0.0008250345,0.000248563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001191265,0.001083236,0.0006085035,0.00004604703,0.0002368527,0.0004910503,0.0002389358,0.3834799,0.02553684,0.335084,0.04111946,0.2119561],"study_design_scores_gemma":[0.000906041,0.0002546273,0.001238639,0.0002859058,0.00001816003,0.00005301232,0.00001402225,0.9681168,0.006401334,0.01681478,0.005342788,0.0005538463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009415596,0.00006466088,0.9752092,0.008873823,0.003722202,0.0003920046,0.00001785583,0.0002568132,0.00204782],"genre_scores_gemma":[0.7557949,0.0001846962,0.2362896,0.004856337,0.001268893,0.0001302649,0.0002564566,0.00004756338,0.001171296],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7463793,"threshold_uncertainty_score":0.9997875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03919903238366152,"score_gpt":0.3092483686304686,"score_spread":0.270049336246807,"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."}}