{"id":"W4312523916","doi":"10.1109/cvpr52688.2022.01509","title":"Multi-Modal Dynamic Graph Transformer for Visual Grounding","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Initialization; Transformer; Ground; Modal; Graph; Ground truth; Artificial intelligence; Data mining; Pattern recognition (psychology); Theoretical computer science; Voltage","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":[0.0005650159,0.0003688363,0.0003653237,0.0004376239,0.001039575,0.0004441537,0.000710237,0.00009134837,0.0004922473],"category_scores_gemma":[0.00001007816,0.0003749699,0.0001879513,0.000423392,0.00006743616,0.0003893496,0.0002021566,0.0006174269,0.0001071482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008733883,"about_ca_system_score_gemma":0.00006091155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001005707,"about_ca_topic_score_gemma":0.00003536862,"domain_scores_codex":[0.9971735,0.0003239765,0.0004807113,0.00104699,0.0005071266,0.0004677348],"domain_scores_gemma":[0.9987014,0.000310492,0.0002179893,0.0004043628,0.0001552035,0.0002105306],"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":[0.00005950466,0.0004801673,0.0004173693,0.00005672762,0.00003875991,0.000009050889,0.0008136295,0.0003573734,0.004087492,0.0005541968,0.0004018028,0.9927239],"study_design_scores_gemma":[0.001949504,0.00118206,0.008995846,0.00006698782,0.00001918654,0.00005783324,0.00007838245,0.983728,0.0002069729,0.002159711,0.001008864,0.00054666],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.215528,0.00001613561,0.7806101,0.001780365,0.0008463611,0.0007482826,0.0001229165,0.0002548278,0.00009300456],"genre_scores_gemma":[0.9668524,0.00003987338,0.02986085,0.002097001,0.0001061019,0.0006090317,0.0002985841,0.00003826294,0.0000978914],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9921772,"threshold_uncertainty_score":0.9998702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04175260766584023,"score_gpt":0.329244912396068,"score_spread":0.2874923047302277,"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."}}