{"id":"W3077527200","doi":"10.1145/3395620","title":"An Adaptive Two-Layer Light Field Compression Scheme Using GNN-Based Reconstruction","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Uncompressed video; Data compression; Data compression ratio; Image compression; Compression (physics); Computer vision; Light field; Compression ratio; Artificial intelligence; Algorithm; Image processing; Image (mathematics); Engineering; Video processing; Materials science","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0001437906,0.0002256213,0.0002165538,0.0001654874,0.001405847,0.0001694321,0.001713974,0.0000798869,0.00001697178],"category_scores_gemma":[0.0000321728,0.000235739,0.0000799242,0.0007151215,0.000133794,0.0005497501,0.0001155235,0.0005317261,0.00002340152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004522408,"about_ca_system_score_gemma":0.00007888459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003866469,"about_ca_topic_score_gemma":0.000006210329,"domain_scores_codex":[0.998424,0.0001683417,0.0004042851,0.000570329,0.0001876487,0.0002454207],"domain_scores_gemma":[0.9964436,0.0006659714,0.0001911715,0.002222529,0.0001869403,0.0002897999],"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":[0.000016356,0.0002810145,0.0001131436,0.000009626269,0.00002018498,3.766647e-7,0.0005528752,0.007102212,0.03785446,0.001575767,0.00001479413,0.9524592],"study_design_scores_gemma":[0.0005960602,0.000124174,0.00006479654,0.00006727364,0.0000185779,0.00001003446,0.0002151379,0.9891811,0.006455073,0.000506418,0.002503169,0.0002582023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001373132,0.0001362709,0.9890758,0.008214354,0.00007161849,0.000488702,0.00001051079,0.000431706,0.0001978921],"genre_scores_gemma":[0.4616252,0.00003832283,0.5372559,0.0009768361,0.00004064019,0.00004061531,0.000008009274,0.00001247426,0.00000203133],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9820789,"threshold_uncertainty_score":0.9998942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06205377170414014,"score_gpt":0.3455773804202104,"score_spread":0.2835236087160703,"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."}}