{"id":"W4401414239","doi":"10.1109/icra57147.2024.10611647","title":"CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Visual servoing; Computer vision; Computer science; Artificial intelligence; Robot; Segmentation; Interface (matter); Expression (computer science); Image segmentation; Human–robot interaction","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":[0.0003118303,0.0001750048,0.0001621126,0.0001696901,0.0003246543,0.0006490658,0.0002387253,0.00007065041,0.00003270658],"category_scores_gemma":[0.00001741652,0.0001331375,0.00007335521,0.0004096812,0.00002076942,0.001116994,0.00008322091,0.000149953,0.00002418106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009052349,"about_ca_system_score_gemma":0.00003493441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001988756,"about_ca_topic_score_gemma":0.000030696,"domain_scores_codex":[0.998493,0.00009375317,0.00034538,0.0005378439,0.0002624243,0.0002676608],"domain_scores_gemma":[0.9994474,0.0001118565,0.00009262992,0.0001736023,0.00009605813,0.00007842156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006346434,0.0000761644,0.0008594048,0.0001718299,0.00005560069,0.000008280788,0.0006060734,0.008151148,0.9685204,0.004820072,0.000379221,0.01628831],"study_design_scores_gemma":[0.0009028023,0.0005279818,0.0006780695,0.0003479448,0.00001905538,0.00001246475,0.0002437444,0.8394179,0.1570921,0.000162925,0.0003600913,0.0002349934],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1292875,0.00002782247,0.8683518,0.0001974907,0.0004574999,0.0003457533,0.000001575971,0.0008372882,0.0004933109],"genre_scores_gemma":[0.9676636,0.000001178758,0.03119342,0.0001385128,0.00009505014,0.00006868535,0.00001185037,0.00002223569,0.0008053952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8383762,"threshold_uncertainty_score":0.6258956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03028229144140852,"score_gpt":0.3464324341251153,"score_spread":0.3161501426837068,"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."}}