{"id":"W2997514790","doi":"10.1609/aaai.v34i07.6783","title":"Deep Generative Probabilistic Graph Neural Networks for Scene Graph Generation","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Scene graph; Probabilistic logic; Generative model; Graph; Theoretical computer science; Minimum bounding box; Pattern recognition (psychology); Generative grammar; Image (mathematics)","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":[],"consensus_categories":[],"category_scores_codex":[0.0003293297,0.0002551606,0.0002613881,0.00008300995,0.0003818216,0.0003085366,0.001751733,0.00009285558,0.00001646889],"category_scores_gemma":[0.0006803833,0.0002014992,0.0001648416,0.0009198263,0.0002138519,0.0003130485,0.0002643566,0.0003379356,0.00001433429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002952904,"about_ca_system_score_gemma":0.00005300487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003973966,"about_ca_topic_score_gemma":0.00001401336,"domain_scores_codex":[0.9980345,0.00003286628,0.0005435964,0.000695923,0.0003489804,0.0003441428],"domain_scores_gemma":[0.9982093,0.0001241078,0.0004155723,0.0002919149,0.0008118959,0.0001471987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004292617,0.00008360852,0.0001831717,0.00003410744,0.00001551065,9.515139e-8,0.001172544,0.06415281,0.02691992,0.8618849,0.0001087651,0.04540166],"study_design_scores_gemma":[0.00003516171,0.0002320866,0.0001558626,0.00002256013,0.00001450451,0.000001198388,0.00005887227,0.8891553,0.04297586,0.06714015,0.00001671713,0.0001917499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03771889,0.00002386481,0.9464791,0.01339174,0.0002602946,0.001467639,0.000004490745,0.0001542659,0.0004996851],"genre_scores_gemma":[0.9661045,0.000008962849,0.03232658,0.0009528251,0.0002667656,0.000307176,0.000003597214,0.00001752153,0.00001207446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9283856,"threshold_uncertainty_score":0.8216898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09663262041000328,"score_gpt":0.3077191104554348,"score_spread":0.2110864900454315,"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."}}