{"id":"W4413925645","doi":"10.1109/icra55743.2025.11127629","title":"MFSeg: Efficient Multi-Frame 3D Semantic Segmentation","year":2025,"lang":"en","type":"article","venue":"","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Frame (networking); Image segmentation; Computer vision; Natural language processing; Computer network","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":[0.00005373207,0.00006655382,0.00007965767,0.000102398,0.00003681154,0.00002423817,0.00004852872,0.00003119174,0.00008060154],"category_scores_gemma":[0.000007366118,0.0000600308,0.00004252613,0.0001942536,0.000005735682,0.00001736271,0.00001155907,0.00005276944,0.0001086784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003151617,"about_ca_system_score_gemma":0.000004851257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002373054,"about_ca_topic_score_gemma":0.00001268292,"domain_scores_codex":[0.9996183,0.000006210944,0.0001165854,0.00009164558,0.00006389429,0.000103369],"domain_scores_gemma":[0.9998342,0.00001436729,0.000005853939,0.0001060448,0.00001930637,0.00002020202],"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":[4.223728e-7,0.0000167638,0.0002048715,0.00002935649,0.00003774961,5.5386e-7,0.000076688,0.9900708,0.003500938,0.00006089454,0.0003858572,0.005615124],"study_design_scores_gemma":[0.000148585,0.000001820016,0.0001856137,0.00001921632,0.00003179725,1.671061e-7,0.00008439663,0.9958553,0.003490069,0.00001540662,0.0001029121,0.00006467537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1357586,0.0001412665,0.8597715,0.0000694978,0.00013355,0.00004102553,8.093877e-7,0.0002921395,0.003791547],"genre_scores_gemma":[0.9865068,0.00001784041,0.01070263,0.00009233436,0.00001199012,0.000006053461,0.000006722757,0.000007105399,0.002648548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8507482,"threshold_uncertainty_score":0.2447985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008717149285301254,"score_gpt":0.2408753274082773,"score_spread":0.232158178122976,"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."}}