{"id":"W4415530757","doi":"10.1016/j.neunet.2025.108232","title":"Internal-external boundary attention fusion for glass surface segmentation","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Information Technology Research Centre; Ministry of Science and ICT, South Korea; Institute for Information and Communications Technology Promotion; Electronics and Telecommunications Research Institute; National Natural Science Foundation of China","keywords":"Boundary (topology); Benchmark (surveying); Surface (topology); Fusion; Task (project management); Segmentation; Exploit","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004474037,0.0008055054,0.000941094,0.001043502,0.0003647235,0.000783385,0.0008081437,0.001129595,0.002698868],"category_scores_gemma":[0.000726354,0.0002694005,0.0007369965,0.0008104016,0.000385348,0.000967858,0.001322465,0.0008108547,0.0007454825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006335959,"about_ca_system_score_gemma":0.0008105299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007331806,"about_ca_topic_score_gemma":0.01040168,"domain_scores_codex":[0.9997205,0.00002621636,0.00001007726,0.00008237887,0.00007522724,0.00008559971],"domain_scores_gemma":[0.9997523,0.00005797782,0.00002473942,0.00004248018,0.00009817812,0.000024154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006053729,0.0001934297,0.001831235,0.0001298552,0.00009273093,0.0001152853,0.00007707794,0.04870062,0.1443695,0.00252212,0.005240425,0.7961224],"study_design_scores_gemma":[0.0000100748,0.00007823836,0.003155292,0.00001286808,0.00006482211,0.0000606094,0.00003106583,0.9550689,0.03806313,0.002047695,0.001393498,0.00001379983],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2014377,0.001746717,0.7837608,0.0004470063,0.0002316426,0.00007774522,0.0003653225,0.00389124,0.008041714],"genre_scores_gemma":[0.8956223,0.0004319538,0.09647729,0.0002650691,0.0001150312,0.00004109132,0.0006513034,0.0002269569,0.006169041],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007331806,"threshold_uncertainty_score":0.01457828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01166002093370501,"score_gpt":0.2523567421843928,"score_spread":0.2406967212506878,"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."}}