{"id":"W4411284470","doi":"10.1007/s11042-025-20946-4","title":"HiSpecmer: a deep efficient image super resolution network using transformers with hierarchical and spectral feature attention","year":2025,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; University of Toronto","funders":"","keywords":"Computer science; Transformer; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Image (mathematics); Superresolution; Computer vision; Voltage; Electrical engineering","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":[0.0001081834,0.0001320989,0.0001283875,0.00007187398,0.0003630207,0.0001957437,0.0001626536,0.00006184366,0.000001064991],"category_scores_gemma":[0.000009819749,0.0001123982,0.00002424936,0.0004416798,0.0002144288,0.0003284234,0.00007105993,0.0001928943,8.554669e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004689578,"about_ca_system_score_gemma":0.00004257234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006607781,"about_ca_topic_score_gemma":0.000008468449,"domain_scores_codex":[0.9990853,0.00002170091,0.0001338057,0.0003980641,0.0001148584,0.0002462898],"domain_scores_gemma":[0.9995535,0.00006562528,0.0000412934,0.0002055597,0.00006124641,0.00007274721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007351161,0.0002498214,0.002044446,0.0001447864,0.00005257578,0.000006373266,0.0007106122,0.001046468,0.08777025,0.05122421,0.0004311462,0.8562458],"study_design_scores_gemma":[0.0004664094,0.00003531437,0.009010634,0.00008350527,0.00003322927,0.00002517648,0.00003403662,0.9809396,0.0009162928,0.004715471,0.003527857,0.0002124798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006551903,0.0006427075,0.9901109,0.001598789,0.00002047786,0.0005329507,0.000005982226,0.0001954669,0.0003407623],"genre_scores_gemma":[0.07444734,0.0001015738,0.9250434,0.0001128707,0.00005935301,0.0001641433,0.0000139282,0.000008305163,0.00004909315],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9798931,"threshold_uncertainty_score":0.4583467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00876387843133815,"score_gpt":0.2613785485364546,"score_spread":0.2526146701051165,"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."}}