{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003338521,0.0004480102,0.0004918115,0.0004624802,0.0003672726,0.0003927623,0.002439064,0.0003349241,0.00001802665],"category_scores_gemma":[0.00005538058,0.0005816605,0.0002943728,0.001239526,0.00005797171,0.0004224318,0.00126012,0.001240549,0.000113892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004579193,"about_ca_system_score_gemma":0.000224581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001885845,"about_ca_topic_score_gemma":0.0001106412,"domain_scores_codex":[0.9966491,0.0002221589,0.0003147085,0.002042614,0.000189391,0.0005820206],"domain_scores_gemma":[0.9976081,0.000102455,0.0002002687,0.001526568,0.0001749634,0.0003876019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003840444,0.001459894,0.006769865,0.0004239581,0.0003746314,0.0001337391,0.004736285,0.7989318,0.002442363,0.1732944,0.00003935804,0.0113552],"study_design_scores_gemma":[0.0005456803,0.00003814145,0.009403799,0.0001246749,0.00007357481,0.000008114811,0.0002863908,0.9878785,0.0001874536,0.0004437067,0.000291622,0.0007183229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3116747,0.00002010597,0.6842224,0.0001109732,0.000167404,0.0004800976,0.000005491342,0.0004055996,0.002913259],"genre_scores_gemma":[0.8859056,0.000027254,0.1132716,0.0001512324,0.00006957598,0.00001378302,0.00004794824,0.00003945392,0.0004735777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5742308,"threshold_uncertainty_score":0.9996635,"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."}}