{"id":"W3211759539","doi":"","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Transformer; Artificial intelligence; Segmentation; Encoder; Ground; Leverage (statistics); Margin (machine learning); Language model; Machine learning; Natural language processing; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001564048,0.001870858,0.001355662,0.0009454204,0.0004458695,0.00152254,0.004068112,0.002296771,0.008222523],"category_scores_gemma":[0.003433327,0.0006985075,0.00191696,0.001021644,0.001044913,0.003855811,0.003430703,0.002688639,0.003112856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009515886,"about_ca_system_score_gemma":0.001289959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005041152,"about_ca_topic_score_gemma":0.006768007,"domain_scores_codex":[0.9989687,0.0002332523,0.00004095257,0.0004314166,0.0001728385,0.000152909],"domain_scores_gemma":[0.999036,0.0003145874,0.00007312128,0.0003378264,0.0001571581,0.00008134598],"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":[0.0005583375,0.000396025,0.0008537921,0.0003130934,0.0002120038,0.0003974185,0.0004753438,0.08983871,0.05497446,0.01746485,0.01407114,0.8204449],"study_design_scores_gemma":[0.00004165968,0.0002443789,0.000524283,0.00002505412,0.0000826632,0.0001866085,0.00009341588,0.9393744,0.0249011,0.02864157,0.005837368,0.00004736028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01336524,0.000483734,0.9673668,0.000334515,0.00008770421,0.0001693556,0.0002914104,0.0146846,0.003216607],"genre_scores_gemma":[0.4804058,0.000517223,0.5019552,0.0008378765,0.0001598831,0.0003295708,0.001555462,0.001262842,0.01297617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008222523,"threshold_uncertainty_score":0.02750707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04019012310903781,"score_gpt":0.3048863225568016,"score_spread":0.2646961994477638,"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."}}