{"id":"W3177140187","doi":"10.1609/aaai.v35i2.16266","title":"Deep Low-Contrast Image Enhancement using Structure Tensor Representation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Contrast (vision); Structure tensor; Image (mathematics); Computer science; Artificial intelligence; Representation (politics); Ground truth; Tensor (intrinsic definition); Pattern recognition (psychology); Function (biology); Deep learning; Image quality; Mathematics; Geometry","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":[0.0002634819,0.0002563116,0.0002861329,0.0001111051,0.0002202702,0.0004581406,0.001508651,0.00009008128,0.0002354504],"category_scores_gemma":[0.0004595182,0.0002113879,0.0001212633,0.0008355455,0.0002176442,0.0008643211,0.0005407383,0.0002906577,0.00003069654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001014823,"about_ca_system_score_gemma":0.0001400688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002504354,"about_ca_topic_score_gemma":0.00001036523,"domain_scores_codex":[0.9976158,0.00003197614,0.0006156334,0.0006850544,0.0006527063,0.0003988741],"domain_scores_gemma":[0.9974863,0.00005579835,0.0004563738,0.0004926689,0.001436786,0.00007206485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001920301,0.0001005834,0.00005631002,0.00003457965,0.00001436613,0.000002402448,0.0006218252,0.00002979039,0.8214142,0.1450363,0.00007668338,0.03259376],"study_design_scores_gemma":[0.00002485062,0.00005522643,0.00007316902,0.0001757298,0.00001232344,0.000009150109,0.0003001369,0.1016396,0.8363397,0.06116218,0.00001761406,0.0001902443],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.183877,0.0000346171,0.8088971,0.001735502,0.00065007,0.0005232054,0.000004276403,0.0001529825,0.004125229],"genre_scores_gemma":[0.9166335,0.0000312621,0.08275943,0.0002726517,0.00009336998,0.0000190796,0.000001314931,0.00001446275,0.000174883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7327566,"threshold_uncertainty_score":0.8620149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05306238292628465,"score_gpt":0.3160405930976323,"score_spread":0.2629782101713477,"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."}}