{"id":"W2804763951","doi":"10.1109/tip.2018.2837341","title":"SPSIM: A Superpixel-Based Similarity Index for Full-Reference Image Quality Assessment","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Special Foundation for the Development of Strategic Emerging Industries of Shenzhen; Shenzhen University; National Natural Science Foundation of China; Nunavut General Monitoring Plan","keywords":"Chrominance; Artificial intelligence; Pattern recognition (psychology); Computer science; Similarity (geometry); Weighting; Image quality; Pixel; Computer vision; Luminance; Pooling; Consistency (knowledge bases); Benchmark (surveying); Image texture; Mathematics; Image (mathematics); Image processing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001338227,0.0004204275,0.0004384943,0.0002780775,0.0012165,0.001158262,0.00103023,0.0001719652,0.00009726756],"category_scores_gemma":[0.00003623632,0.0004143653,0.0002204168,0.0007121764,0.0003781216,0.002335592,0.00001254086,0.000550958,0.00005251608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002688637,"about_ca_system_score_gemma":0.001029925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008518418,"about_ca_topic_score_gemma":0.0001420015,"domain_scores_codex":[0.996506,0.0002779834,0.0007254064,0.001024547,0.0007278631,0.0007381864],"domain_scores_gemma":[0.9972249,0.0003357583,0.0002543354,0.0009658109,0.000995042,0.0002241949],"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":[0.0007430241,0.004867131,0.0001125976,0.002040192,0.0001874401,0.00003956326,0.003093076,0.0007689901,0.3426001,0.00209597,0.001481598,0.6419703],"study_design_scores_gemma":[0.003226425,0.001063768,0.001023922,0.0002943076,0.00009248228,0.00001687775,0.0004021679,0.6704959,0.3162264,0.003772595,0.002096036,0.001289201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004015057,0.00001954201,0.9905296,0.002585335,0.0004629043,0.00060962,0.00007087795,0.0004798611,0.001227209],"genre_scores_gemma":[0.6563019,0.000002558952,0.3420271,0.001229818,0.00009541716,0.000186894,0.000006037973,0.00002679864,0.0001234511],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6697268,"threshold_uncertainty_score":0.9998786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07463002403551655,"score_gpt":0.3891517343290542,"score_spread":0.3145217102935376,"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."}}