{"id":"W7117785157","doi":"10.1016/j.eswa.2025.130945","title":"SSVA: Self-scanned visual attention for enhanced mask-free shadow removal","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Alfaisal University; Prince Sultan University","keywords":"Shadow (psychology); Benchmark (surveying); Channel (broadcasting); Mean squared error; Feature (linguistics); Pattern recognition (psychology); Shadow mask; Feature extraction","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001653214,0.0002725844,0.0002999592,0.0001732814,0.0006218718,0.0001809411,0.00118086,0.00011016,0.000001885924],"category_scores_gemma":[0.00001923987,0.0002478003,0.00009524744,0.001328409,0.00005969589,0.000394428,0.0002282019,0.0001262846,0.00004668902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001891913,"about_ca_system_score_gemma":0.0001388354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003070238,"about_ca_topic_score_gemma":0.00002643796,"domain_scores_codex":[0.9978377,0.00005004009,0.0004844829,0.0009034225,0.0002769068,0.000447506],"domain_scores_gemma":[0.9973425,0.0002303829,0.000247592,0.001751139,0.0002976798,0.000130755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004470731,0.0004121715,0.00005344077,0.0001295513,0.0001396837,0.000002168947,0.0003952927,0.001321956,0.03723745,0.9279135,0.01764113,0.01470898],"study_design_scores_gemma":[0.003664798,0.0003050787,0.0005322105,0.000302213,0.00007913541,0.0001218191,0.0005693419,0.2146879,0.01264749,0.01902667,0.746753,0.001310316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005051487,0.0006847486,0.9868793,0.002767373,0.0002415713,0.003992593,0.0000155675,0.0009978517,0.00391584],"genre_scores_gemma":[0.5284509,0.00007246296,0.4258425,0.0006963596,0.0005730215,0.03894525,0.00009074989,0.00005836716,0.005270351],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9088868,"threshold_uncertainty_score":0.9999974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00870717423581578,"score_gpt":0.2810863656059223,"score_spread":0.2723791913701065,"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."}}