{"id":"W3091086757","doi":"10.1109/iscas45731.2020.9181230","title":"PHMNet: A Deep Super Resolution Network using Parallel and Hierarchical Multi-Scale Residual Blocks","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Residual; Block (permutation group theory); Computer science; Abstraction; Artificial intelligence; Image (mathematics); Set (abstract data type); Scale (ratio); Pattern recognition (psychology); Scheme (mathematics); Deep learning; Algorithm; Mathematics","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":[0.0001622377,0.000153524,0.0001695515,0.0000350637,0.0002202364,0.0001590796,0.0004445295,0.00008179516,0.000008505678],"category_scores_gemma":[0.00006695704,0.0001407901,0.00002809559,0.00031956,0.000128469,0.0006072682,0.0005951233,0.0002462544,0.000003823751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001860637,"about_ca_system_score_gemma":0.00004384795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001690518,"about_ca_topic_score_gemma":0.0000143924,"domain_scores_codex":[0.998626,0.00006981463,0.0002167655,0.0005237699,0.0001960697,0.0003676052],"domain_scores_gemma":[0.9993904,0.0000542289,0.00004929886,0.000270624,0.00005683641,0.0001786672],"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":[0.0009105119,0.001096077,0.0360972,0.0005325008,0.0002294401,0.0006357912,0.03011138,0.08978144,0.2642554,0.07737742,0.03677493,0.4621979],"study_design_scores_gemma":[0.0002886882,0.00006668779,0.0003837587,0.00002087116,0.000004973842,0.00002733172,0.00001321264,0.9923523,0.0006822916,0.004866582,0.001095949,0.0001973449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002069404,0.0005674202,0.9933334,0.002808734,0.00003364685,0.0001425956,4.906598e-7,0.0007145272,0.0003297915],"genre_scores_gemma":[0.06179265,0.00002336635,0.9362161,0.001737349,0.0001562163,0.000007710535,0.000001126992,0.00001345851,0.00005206606],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9025708,"threshold_uncertainty_score":0.5741254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04072073289056711,"score_gpt":0.2861463054904447,"score_spread":0.2454255725998776,"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."}}