{"id":"W3157108758","doi":"10.1109/iccv48922.2021.01558","title":"Segmentation-grounded Scene Graph Generation","year":2021,"lang":"en","type":"preprint","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Air Force; Compute Canada; Defense Advanced Research Projects Agency; Air Force Research Laboratory; Government of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Scene graph; Segmentation; Graph; Pixel; Bounding overwatch; Pattern recognition (psychology); Granularity; Computer vision; Image segmentation; Object (grammar); Theoretical computer science","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005654541,0.000772175,0.0006313597,0.0007291581,0.0003794547,0.003397262,0.003430663,0.0004554813,0.001018879],"category_scores_gemma":[0.00005651338,0.0008228227,0.0004261938,0.0005350643,0.00008517941,0.0007256211,0.002128794,0.001505322,0.0004931976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000546116,"about_ca_system_score_gemma":0.0005999462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007335012,"about_ca_topic_score_gemma":0.0001138156,"domain_scores_codex":[0.9938745,0.000505621,0.001087831,0.00232497,0.001720491,0.0004865205],"domain_scores_gemma":[0.9951552,0.0002130575,0.000799057,0.001935054,0.001609956,0.0002877371],"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":[0.00007407671,0.002012025,0.0007447541,0.0001547773,0.0008929053,0.0002241118,0.002221656,0.1545737,0.04505915,0.2274094,0.01761184,0.5490215],"study_design_scores_gemma":[0.000670346,0.0001596706,0.003546299,0.0003891233,0.0000245787,0.0000300472,0.00002737929,0.9856494,0.003544731,0.004471726,0.0006857833,0.0008009083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05873381,0.00005258126,0.9182375,0.009479547,0.008952981,0.0007207353,0.00005961736,0.0003576954,0.003405533],"genre_scores_gemma":[0.749262,0.0002070536,0.2450581,0.001421205,0.001723306,0.000266311,0.00142935,0.00005225285,0.0005803839],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8310757,"threshold_uncertainty_score":0.9998943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06238528048595809,"score_gpt":0.3508478787254485,"score_spread":0.2884625982394904,"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."}}