{"id":"W4409379681","doi":"10.1016/j.autcon.2025.106160","title":"Temporal defect point localization in pipe CCTV videos with transformers","year":2025,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Wave Control Systems (Canada)","funders":"National Key Research and Development Program of China; Natural Science Foundation of Tianjin City","keywords":"Transformer; Computer vision; Point (geometry); Artificial intelligence; Computer science; Engineering; Computer graphics (images); Engineering drawing; Electrical engineering; Mathematics; Geometry; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002977566,0.0001099374,0.0001610832,0.0007625548,0.00007544283,0.0001351158,0.0001352804,0.00008022543,0.00001854305],"category_scores_gemma":[0.00003596325,0.0001030616,0.00004608682,0.002170891,0.00004354748,0.001222407,0.00001686114,0.0000908992,0.000007721159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001712983,"about_ca_system_score_gemma":0.0001252121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005001432,"about_ca_topic_score_gemma":0.001333437,"domain_scores_codex":[0.9988191,0.0001185614,0.0004282172,0.000292585,0.0001923999,0.0001491353],"domain_scores_gemma":[0.9995484,0.00004337035,0.0001082907,0.0001775308,0.00009825247,0.00002416915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002621849,0.0001116505,0.5708119,0.00008170524,0.00004043951,0.000004972481,0.0009969732,0.03883724,0.0004954009,0.06356874,0.0001582523,0.3248665],"study_design_scores_gemma":[0.00087322,0.00004257768,0.05578499,0.0001400708,0.00001195948,0.000008411237,0.0002826374,0.9328223,0.001099775,0.008621627,0.0001592075,0.0001532203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07142264,0.00001715396,0.9252979,0.001024369,0.0001627643,0.0002866951,4.519437e-7,0.0001243372,0.00166368],"genre_scores_gemma":[0.9875051,0.00001154801,0.01220151,0.0001779354,0.000007504315,0.00004696634,0.00002528855,0.000004159667,0.00002000812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9160824,"threshold_uncertainty_score":0.4202728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003875139273909797,"score_gpt":0.2171302141857437,"score_spread":0.2132550749118339,"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."}}