{"id":"W4322730980","doi":"10.1109/jstsp.2023.3250956","title":"Attentive Deep Image Quality Assessment for Omnidirectional Stitching","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Image stitching; Computer vision; Artificial intelligence; Omnidirectional antenna; Computer science; Image quality; Quality (philosophy); Quality assessment; Feature extraction; Image (mathematics); Evaluation methods; Telecommunications; 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":[0.002231162,0.0001596831,0.000341838,0.0004000015,0.0002424726,0.0003713928,0.0005503704,0.00007834629,0.000006616465],"category_scores_gemma":[0.0001566861,0.0001491123,0.0001206445,0.001287437,0.00003757383,0.001418104,0.00006469961,0.0005031308,0.000002590086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002744475,"about_ca_system_score_gemma":0.000738964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000130227,"about_ca_topic_score_gemma":0.0000160615,"domain_scores_codex":[0.9975886,0.0002401764,0.000870801,0.0002675156,0.000649205,0.0003837199],"domain_scores_gemma":[0.9976666,0.0003882752,0.0006060092,0.0001255792,0.001128227,0.00008533553],"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":[0.0001955264,0.0009734903,0.008219977,0.0008169784,0.0002605446,0.0003235935,0.008238495,0.007621409,0.204003,0.007708089,0.002073046,0.7595658],"study_design_scores_gemma":[0.005397868,0.001077079,0.1384143,0.00117985,0.00009283384,0.0002622253,0.001864471,0.7086147,0.06204828,0.07736428,0.002382131,0.001302005],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07801876,0.0001020055,0.9194661,0.001480035,0.0004600497,0.0001469372,0.000001855461,0.00006554108,0.0002586637],"genre_scores_gemma":[0.8249426,0.00002042117,0.1739942,0.0002105769,0.0006738916,0.0000139088,0.000003226683,0.0000143338,0.0001268232],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7582638,"threshold_uncertainty_score":0.6080624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05969875639345208,"score_gpt":0.3890157431510267,"score_spread":0.3293169867575746,"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."}}