{"id":"W3171547673","doi":"10.48550/arxiv.2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ground; Transformer; Task (project management); Computer science; Engineering; Electrical engineering; Systems engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00172239,0.001972593,0.001359598,0.001030474,0.0004758947,0.001591524,0.004138933,0.002391988,0.008347004],"category_scores_gemma":[0.003703319,0.0007253333,0.002077588,0.001100013,0.001107975,0.00390222,0.003651001,0.002805115,0.003447182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009918535,"about_ca_system_score_gemma":0.001301407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005109534,"about_ca_topic_score_gemma":0.006959579,"domain_scores_codex":[0.9988501,0.0002736245,0.00004359276,0.0004848782,0.0001836299,0.0001641372],"domain_scores_gemma":[0.9989595,0.0003381002,0.00007443676,0.0003743665,0.0001689659,0.00008460917],"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":[0.0005542723,0.000396482,0.0009274456,0.0003114812,0.000213932,0.0003953745,0.0004915165,0.08682006,0.04995555,0.01835003,0.01629636,0.8252875],"study_design_scores_gemma":[0.00004354789,0.0002435754,0.0005558015,0.00002843854,0.00008521201,0.0001981535,0.0001012522,0.935035,0.02479108,0.03223751,0.006631169,0.00004911618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01262489,0.0004878113,0.9666355,0.0003600203,0.00009123266,0.0001723832,0.0003245392,0.01598119,0.003322434],"genre_scores_gemma":[0.4607449,0.0005346221,0.5201771,0.0009398941,0.0001780024,0.0003539223,0.001854519,0.001426605,0.0137905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008347004,"threshold_uncertainty_score":0.02792352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1171326450951862,"score_gpt":0.2384591119005074,"score_spread":0.1213264668053212,"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."}}