{"id":"W4402650689","doi":"10.1186/s40494-024-01441-9","title":"Automatic defect detection in infrared thermal images of ancient polyptychs based on numerical simulation and a new efficient channel attention mechanism aided Faster R-CNN model","year":2024,"lang":"en","type":"article","venue":"Heritage Science","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"National Key Research and Development Program of China; Ministero dell’Istruzione, dell’Università e della Ricerca; Ministry of Science and Technology of the People's Republic of China","keywords":"Mechanism (biology); Infrared; Channel (broadcasting); Thermal; Computer science; Artificial intelligence; Computer vision; Simulation; Optics; Telecommunications; Physics; Thermodynamics","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":[0.0006824369,0.000144686,0.0001451299,0.0005246229,0.0001618621,0.0003436145,0.0002550788,0.00005239819,0.00000436666],"category_scores_gemma":[0.00008897869,0.0001261193,0.00005878976,0.001311468,0.000147673,0.0007794367,0.00008615148,0.0001377429,0.000006538856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000102481,"about_ca_system_score_gemma":0.0002732073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001803474,"about_ca_topic_score_gemma":0.000002034426,"domain_scores_codex":[0.9983389,0.00005813396,0.0002719569,0.000557128,0.0004851926,0.0002886468],"domain_scores_gemma":[0.9994329,0.00007008323,0.00008693282,0.0002446614,0.00007134605,0.00009409338],"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":[0.00001407081,0.00006901696,0.00003528033,0.0001213875,0.000002554229,0.000006870644,0.001275653,0.5754046,0.1891951,0.0002747502,0.000001657189,0.233599],"study_design_scores_gemma":[0.0002461323,0.0001102825,0.002473974,0.000192397,0.000005090605,0.00001017774,0.00004818254,0.9671996,0.02863967,0.0009427046,5.603545e-7,0.0001312767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3966426,0.00006971833,0.6026342,0.00005213946,0.0002637844,0.0001234775,6.344168e-7,0.0001084356,0.000105023],"genre_scores_gemma":[0.9775474,7.374691e-7,0.02230101,0.0000746416,0.00001860893,0.00001054931,4.082692e-7,0.000008408474,0.00003824348],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5809048,"threshold_uncertainty_score":0.5142998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01592490235838644,"score_gpt":0.2559584377711221,"score_spread":0.2400335354127357,"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."}}